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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54506
    Prev
    Next
    INDEX
    Explanations

    key-value identifiers

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

    The neuron activates on numeric literal tokens (integer or decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    unno
    -1.16
    ប
    -1.05
    ebly
    -1.04
    咐
    -1.03
    foundland
    -1.02
    入
    -1.01
    ridescent
    -0.99
    𝗢
    -0.98
    école
    -0.97
    ندما
    -0.97
    POSITIVE LOGITS
     salonu
    1.18
    ############
    1.08
     like
    1.02
    🐈
    1.00
    Kolor
    1.00
    ...).
    1.00
    мне
    1.00
    ֧
    0.99
     äls
    0.98
    彼らの
    0.97
    Activations Density 0.023%

    No Known Activations