© 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. 77828
    Prev
    Next
    INDEX
    Explanations

    permitted provided

    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
     by
    -0.82
     although
    -0.75
     three
    -0.75
    上映
    -0.72
    timeout
    -0.71
     as
    -0.70
     undeniably
    -0.70
    ựu
    -0.68
     گیل
    -0.68
     because
    -0.68
    POSITIVE LOGITS
     boîtes
    0.76
    ᴠ
    0.76
    ceptive
    0.76
    sbs
    0.72
     каждый
    0.70
     Vicente
    0.69
    llan
    0.69
    riculum
    0.69
     prácticas
    0.68
     鶏
    0.68
    Activations Density 0.040%

    No Known Activations