© 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. 34-GEMMASCOPE-RES-131K
    7. 108035
    Prev
    Next
    INDEX
    Explanations

    internal feelings or states

    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_34/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
     hands
    -0.85
    デーション
    -0.78
     personnage
    -0.77
    allen
    -0.76
     infección
    -0.71
    行為
    -0.69
    hecimento
    -0.69
     hand
    -0.69
    person
    -0.69
     Celebr
    -0.69
    POSITIVE LOGITS
    slavery
    0.93
     slavery
    0.91
     heartfelt
    0.90
     péné
    0.90
     feelings
    0.89
     impressions
    0.86
     conviction
    0.84
    🪔
    0.84
     thrills
    0.83
    Réalisation
    0.82
    Activations Density 0.015%

    No Known Activations