© 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. 34-GEMMASCOPE-RES-131K
    7. 3181
    Prev
    Next
    INDEX
    Explanations

    subject to change

    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_34/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
    PORTS
    -0.84
    まい
    -0.81
    ův
    -0.77
    '';
    -0.77
    thunk
    -0.77
    .*,
    -0.77
    umum
    -0.76
    Decay
    -0.75
    问题
    -0.75
    的问题
    -0.74
    POSITIVE LOGITS
     subject
    3.69
    subject
    3.30
    Subject
    2.64
     Subject
    2.53
     SUBJECT
    2.14
    getSubject
    2.06
     sujeto
    2.06
    SUBJECT
    1.98
     sujet
    1.86
     soggetto
    1.84
    Activations Density 0.043%

    No Known Activations