© 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. 117593
    Prev
    Next
    INDEX
    Explanations

    email message separators like -----

    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
     maat
    -0.86
     WELCOME
    -0.81
    码
    -0.78
     WANT
    -0.76
    Ꮂ
    -0.75
     первых
    -0.74
    &&(
    -0.73
     کردیم
    -0.73
     Poste
    -0.73
    compared
    -0.73
    POSITIVE LOGITS
    Sent
    1.27
     Sent
    1.06
    -----
    1.05
    Attachments
    1.04
    From
    1.02
    ________________
    1.02
     forwarded
    1.01
    On
    0.94
    Original
    0.94
    CAUTION
    0.90
    Activations Density 0.106%

    No Known Activations