© 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. 85492
    Prev
    Next
    INDEX
    Explanations

    dice rolling and RPGs

    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
     machten
    -1.53
    U
    -1.51
     vechi
    -1.51
    媜
    -1.49
     bancaria
    -1.49
     вновь
    -1.48
    作った
    -1.43
     despues
    -1.39
     Uniwers
    -1.39
    ŧ
    -1.38
    POSITIVE LOGITS
     or
    1.68
    ｘ
    1.48
    IDADES
    1.44
    あります
    1.44
     of
    1.43
    嗚
    1.42
    喽
    1.39
    ｹ
    1.39
    關於
    1.38
    Wymiary
    1.37
    Activations Density 0.004%

    No Known Activations