© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 86169
    Prev
    Next
    INDEX
    Explanations

    sequences appearing together

    np_acts-logits-general · gemini-2.5-flash-lite

    people based on personality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    㝢
    0.47
     منك
    0.46
    ars
    0.45
     ք
    0.45
    দ্যাল
    0.44
     كات
    0.44
    ujú
    0.44
     két
    0.44
     engend
    0.44
    tać
    0.43
    POSITIVE LOGITS
    chance
    0.49
     ширина
    0.47
    injury
    0.47
    o
    0.47
    act
    0.46
    in
    0.46
     fatigue
    0.45
    itemView
    0.45
    a
    0.45
    p
    0.44
    Activations Density 0.000%

    No Known Activations