© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130197
    Prev
    Next
    INDEX
    Explanations

    mathematical derivatives and specific tokens

    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_22/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
    Nhan
    -1.04
    sakura
    -1.03
    câ
    -0.96
     legyen
    -0.94
    chó
    -0.94
    }=\
    -0.89
     てき
    -0.88
    óstico
    -0.88
    món
    -0.88
    állítás
    -0.88
    POSITIVE LOGITS
    Và
    0.87
    ≜
    0.87
     avantaj
    0.86
     ними
    0.85
     etk
    0.84
     insiste
    0.84
    苜
    0.83
    menden
    0.83
    Приятного
    0.82
    之战
    0.82
    Activations Density 0.055%

    No Known Activations