© 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. 45236
    Prev
    Next
    INDEX
    Explanations

    The Evil Within, Death Eraser, Grimoire

    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
    філь
    -1.54
     inmiddels
    -1.39
     männer
    -1.38
    acceso
    -1.35
     meestal
    -1.35
    欤
    -1.34
    –¿
    -1.30
    borsa
    -1.27
     decorados
    -1.27
    wiches
    -1.24
    POSITIVE LOGITS
     even
    1.72
    r
    1.60
    );
    1.55
     also
    1.48
     [];
    1.39
     However
    1.38
     Therefore
    1.38
    ];
    1.37
    P
    1.35
    虽
    1.31
    Activations Density 0.127%

    No Known Activations