© 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. 68256
    Prev
    Next
    INDEX
    Explanations

    scoring points

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

    Number followed by "point" or "points"

    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
     GoObject
    0.42
    าว
    0.41
     Disabilities
    0.41
     Signaling
    0.41
    ป
    0.41
    ب
    0.41
     Groups
    0.40
    雳
    0.40
    ပ
    0.40
     leftWheel
    0.40
    POSITIVE LOGITS
    rado
    0.45
    omatik
    0.43
     hangi
    0.43
    rf
    0.42
    thats
    0.41
     garantie
    0.40
    suit
    0.40
    ffected
    0.40
    hangi
    0.40
     এতটাই
    0.39
    Activations Density 0.001%

    No Known Activations