© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20772
    Prev
    Next
    INDEX
    Explanations

    Ca2+ channel activation or factors

    np_acts-logits-general · gemini-2.5-flash-lite

    alphanumeric sequences and identifiers in code or technical documentation.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is detecting tokens that are numeric sequences (i.e. multi‐digit numbers or numbers embedded in identifiers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    為に
    -2.25
    来週
    -2.19
    ところに
    -2.19
    感じで
    -2.17
    つづく
    -2.09
     arşivlendi
    -2.03
    ナメント
    -2.02
    corrhi
    -1.98
    んですよ
    -1.98
    ditionally
    -1.97
    POSITIVE LOGITS
    <bos>
    2.38
    などが
    2.30
    もあって
    2.23
    前は
    2.20
    がありますが
    2.19
    って思
    2.05
    そして
    2.03
    があり
    1.98
    などを
    1.95
    BURGH
    1.95
    Activations Density 31.299%

    No Known Activations