© 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. 67092
    Prev
    Next
    INDEX
    Explanations

    meetings and events

    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
     anún
    -2.33
     desempen
    -2.19
     banyo
    -2.02
    zocht
    -1.98
    และ
    -1.94
     vetores
    -1.92
     内衣
    -1.90
     esquecer
    -1.88
     suhu
    -1.85
    tienen
    -1.84
    POSITIVE LOGITS
    (
    3.16
    ll
    2.44
    al
    2.30
    <bos>
    2.17
    For
    2.09
    大部分
    2.08
     debatable
    2.06
    In
    2.02
    もちろん
    1.99
    ta
    1.96
    Activations Density 0.013%

    No Known Activations