© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73901
    Prev
    Next
    INDEX
    Explanations

    terrain and terrains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    d
    -2.69
     花卉
    -2.63
    嫗
    -2.55
     It
    -2.48
    譟
    -2.28
     笔画
    -2.27
     lancia
    -2.25
    Ꮠ
    -2.22
    忉
    -2.19
    紲
    -2.19
    POSITIVE LOGITS
    "
    2.83
     alguns
    2.75
     speziellen
    2.53
    逦
    2.50
     entspre
    2.44
     
    2.44
     are
    2.39
    ?
    2.31
     "
    2.27
    蚡
    2.22
    Activations Density 0.001%

    No Known Activations