© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73374
    Prev
    Next
    INDEX
    Explanations

    therefore, hence, thus

    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
    "]];
    -1.09
     così
    -1.09
     lecciones
    -1.02
    vosti
    -0.99
     sebagainya
    -0.96
     These
    -0.95
     Kluwer
    -0.95
    ˍ
    -0.95
     estómago
    -0.92
    anolamine
    -0.91
    POSITIVE LOGITS
    ,
    1.13
     “
    1.06
     instead
    1.04
     able
    1.03
    ものを
    1.02
    <strong>
    1.02
    多少
    1.01
    She
    0.99
    才有
    0.99
    eezy
    0.96
    Activations Density 0.044%

    No Known Activations