© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3754
    Prev
    Next
    INDEX
    Explanations

    lists data or operations

    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
    ,
    0.81
     ag
    0.80
    !,
    0.76
     al
    0.74
     focused
    0.74
     with
    0.72
     occasion
    0.71
     focussed
    0.68
     other
    0.67
     sooner
    0.63
    POSITIVE LOGITS
    odh
    1.90
     perut
    1.83
    Whe
    1.77
    结尾
    1.75
    Final
    1.74
    ٨
    1.74
    ebd
    1.74
    qh
    1.74
     cayó
    1.73
    дона
    1.72
    Activations Density 0.080%

    No Known Activations