© 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. 4491
    Prev
    Next
    INDEX
    Explanations

    millions displaced

    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
    .
    1.88
    '
    1.71
    ,
    1.70
    .—
    1.65
    ’
    1.54
    ↵↵
    1.48
    astic
    1.47
    ﹗
    1.46
    ­
    1.45
     that
    1.43
    POSITIVE LOGITS
     undefined
    3.55
     approx
    3.50
     negligible
    3.37
    rinsic
    3.24
    7
    3.10
     habitable
    3.05
     unisex
    3.04
     distinguishable
    3.01
     uninhab
    2.95
     pristine
    2.92
    Activations Density 0.235%

    No Known Activations