© 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. 68366
    Prev
    Next
    INDEX
    Explanations

    personal feelings and thoughts

    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
     a
    -2.28
    :
    -1.77
     is
    -1.76
     it
    -1.75
    _
    -1.70
    ]
    -1.55
    了不少
    -1.55
     puede
    -1.51
     récentes
    -1.48
     literaria
    -1.46
    POSITIVE LOGITS
    investissement
    1.54
     Accesorios
    1.52
     工場
    1.51
    なども
    1.48
     impos
    1.47
     tohoto
    1.45
    ここから
    1.41
    décoration
    1.40
     começ
    1.31
    全世界
    1.31
    Activations Density 0.016%

    No Known Activations