© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2463
    Prev
    Next
    INDEX
    Explanations

    driving conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Oogie
    1.34
     Dominguez
    1.28
    cadia
    1.24
     numbness
    1.23
     mapDispatch
    1.23
    鞆
    1.22
    chemia
    1.22
     slashing
    1.19
    hesia
    1.19
     Autón
    1.19
    POSITIVE LOGITS
    .
    0.86
    ge
    0.84
     concepts
    0.81
     Ce
    0.81
    Fest
    0.81
    �
    0.77
    con
    0.77
     criteria
    0.76
    ?
    0.76
     P
    0.75
    Activations Density 0.038%

    No Known Activations