© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 25903
    Prev
    Next
    INDEX
    Explanations

    programming, code, markup

    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
     Ancho
    -0.94
    funeralhome
    -0.76
     ABCD
    -0.75
    USO
    -0.75
     CASA
    -0.73
    💀
    -0.73
    Вопрос
    -0.72
    versorgung
    -0.70
     dessus
    -0.70
     titul
    -0.69
    POSITIVE LOGITS
    ľ
    0.77
    presidente
    0.71
    ͫ
    0.70
    pagnols
    0.69
     attachments
    0.64
    クラブ
    0.64
    méno
    0.63
    ोजना
    0.63
    σσ
    0.63
    guardian
    0.63
    Activations Density 0.035%

    No Known Activations