© 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. 22-GEMMASCOPE-RES-131K
    7. 73405
    Prev
    Next
    INDEX
    Explanations

    names and specific nouns

    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
     baixa
    -0.80
    >());
    -0.79
     ję
    -0.77
     conosco
    -0.77
    +"/"+
    -0.76
    mL
    -0.75
     {};
    -0.75
    当年
    -0.74
     represented
    -0.74
    éroport
    -0.74
    POSITIVE LOGITS
     Incluso
    0.91
     Aún
    0.91
     Algunas
    0.91
     carolina
    0.89
     appreci
    0.89
    }$\\
    0.84
     Había
    0.84
     Algunos
    0.83
     Voyez
    0.83
    Сан
    0.82
    Activations Density 0.037%

    No Known Activations