© 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. 74430
    Prev
    Next
    INDEX
    Explanations

    Tracker, vehicles

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

    driving speed limits

    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
     $\%$
    0.45
     子供
    0.41
     UWGM
    0.40
    newspaper
    0.40
    通常の
    0.40
    )-$
    0.40
    ItemStack
    0.39
     パンツ
    0.38
    <0x8D>
    0.38
    উক
    0.38
    POSITIVE LOGITS
     Prosecutor
    0.47
     Prosec
    0.46
    Dee
    0.45
    Prosec
    0.45
     hool
    0.43
     prosec
    0.43
     Hoo
    0.42
    Bes
    0.42
    äär
    0.42
     canal
    0.41
    Activations Density 0.086%

    No Known Activations