© 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. 34-GEMMASCOPE-RES-131K
    7. 47483
    Prev
    Next
    INDEX
    Explanations

    like or style

    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
    INAR
    -0.91
     Mehrheit
    -0.90
     lần
    -0.89
     bezeichnet
    -0.88
    的脸
    -0.86
    Răsp
    -0.85
    壁纸
    -0.84
    惮
    -0.83
     αυτή
    -0.82
    ོན་
    -0.82
    POSITIVE LOGITS
    like
    3.64
     style
    2.70
     type
    2.61
    LIKE
    2.52
    ähn
    2.39
    esque
    2.31
    のような
    2.22
    style
    2.20
     like
    2.19
    type
    2.14
    Activations Density 0.475%

    No Known Activations