© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 1909
    Prev
    Next
    INDEX
    Explanations

    throughout the day/year/lifecycle

    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_16k_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
    ắm
    1.08
    raf
    0.82
    ตรี
    0.81
    k
    0.80
    mina
    0.78
     altra
    0.75
    One
    0.74
    ंबा
    0.69
    kej
    0.65
     nowych
    0.65
    POSITIVE LOGITS
    整个
    2.53
    سترول
    2.49
    jectories
    2.48
    ♾
    2.42
     时间
    2.41
     maddi
    2.39
     andolan
    2.39
     eul
    2.36
     cytometry
    2.33
     iterates
    2.33
    Activations Density 0.091%

    No Known Activations