© 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. 22-GEMMASCOPE-RES-131K
    7. 26865
    Prev
    Next
    INDEX
    Explanations

    identifier, account, LOCATION

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    dekat
    -1.34
    '>"
    -1.12
    '");
    -1.05
     who
    -1.05
    头像
    -1.04
    ⁼
    -1.03
    ☎️
    -1.01
    ırlar
    -1.01
    вале
    -1.01
    の為
    -1.01
    POSITIVE LOGITS
     ciertos
    1.09
     essas
    1.03
     değişik
    1.02
     Situationen
    1.02
    om
    1.00
    or
    1.00
    um
    0.99
     Different
    0.99
     diversos
    0.99
     condol
    0.97
    Activations Density 0.001%

    No Known Activations