© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6908
    Prev
    Next
    INDEX
    Explanations

    rib cuts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_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
     sean
    0.97
     Phoenix
    0.89
     @
    0.89
    eng
    0.88
    <h3>
    0.87
    </h3>
    0.83
     su
    0.82
    </td>
    0.81
     doğ
    0.80
    <h4>
    0.80
    POSITIVE LOGITS
    பின்னர்
    1.20
    뺀
    1.16
    ₁+
    1.11
    மர்
    1.11
    ॔
    1.10
    MaxScaler
    1.10
    ToolStrip
    1.10
    之后
    1.09
    තික
    1.09
     분포
    1.08
    Activations Density 0.000%

    No Known Activations