© 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. 39619
    Prev
    Next
    INDEX
    Explanations

    certain points

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

    transaction, social, root canal, dreams

    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
    ච්
    0.52
    corre
    0.49
    紙
    0.46
    يري
    0.46
    đe
    0.44
     کوي
    0.43
    вач
    0.43
    izie
    0.43
    արդ
    0.43
    <0x99>
    0.42
    POSITIVE LOGITS
     amount
    0.47
     Grüße
    0.47
    ne
    0.47
     assets
    0.46
     Living
    0.46
     itineraries
    0.46
     unsaturated
    0.45
     Observatory
    0.45
     AMOUNT
    0.45
     오는
    0.45
    Activations Density 0.000%

    No Known Activations