© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 123802
    Prev
    Next
    INDEX
    Explanations

    sold in, discover if, service including

    np_acts-logits-general · gemini-2.5-flash-lite

    Straight Pride

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ప్రతి
    0.62
     స్థ
    0.54
     प्रत्येक
    0.54
    <unused26>
    0.52
     მა
    0.52
     प्रव
    0.52
     संपादक
    0.52
    ٦
    0.52
     შეიძ
    0.51
    <unused30>
    0.51
    POSITIVE LOGITS
    l
    0.55
     cruise
    0.46
     northward
    0.42
     gently
    0.42
    CW
    0.41
    flux
    0.40
    def
    0.40
    PY
    0.39
     westward
    0.39
    glow
    0.38
    Activations Density 0.001%

    No Known Activations