© 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. 69083
    Prev
    Next
    INDEX
    Explanations

    signals, pigs, Age, crossings, compensation, animal, throat, bamboo, BB, Metal, negative

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

    words or concepts related to specific industries, businesses, or professional fields.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    比如
    -1.55
     such
    -1.50
     including
    -1.47
    ㈠
    -1.33
    مثل
    -1.30
    例えば
    -1.30
    INCLUDING
    -1.28
     včetně
    -1.25
     dwóch
    -1.24
    landı
    -1.23
    POSITIVE LOGITS
     or
    1.18
    Y
    1.15
    ;/
    1.14
    O
    1.13
     ">=
    1.13
    ()
    1.11
    U
    1.10
    E
    1.10
    imetry
    1.08
     etc
    1.05
    Activations Density 0.084%

    No Known Activations