© 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. 117116
    Prev
    Next
    INDEX
    Explanations

    names, titles, or code snippets

    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
    newcommand
    -0.78
     أهم
    -0.77
     св
    -0.76
     Bühne
    -0.75
    érie
    -0.73
     berjudul
    -0.73
    逻辑
    -0.72
    CELONA
    -0.72
     inolvid
    -0.72
     Bible
    -0.72
    POSITIVE LOGITS
     amongst
    0.88
    ఇ
    0.85
    Parmi
    0.82
     novedad
    0.80
    ėms
    0.79
     Ibn
    0.76
    Regel
    0.76
     SafeArea
    0.76
    authToken
    0.76
     fantaisie
    0.75
    Activations Density 0.007%

    No Known Activations