© 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. 57513
    Prev
    Next
    INDEX
    Explanations

    copyright notices license keywords

    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
    articulo
    -0.79
    arie
    -0.79
    downarrow
    -0.71
    ″]
    -0.70
     insight
    -0.67
    EVEN
    -0.65
    worth
    -0.65
    걷
    -0.65
    getic
    -0.64
     quedarse
    -0.64
    POSITIVE LOGITS
     ಇ
    0.73
    𝖓
    0.71
     Platforms
    0.69
     puro
    0.69
     recompensa
    0.69
    Tough
    0.68
     dates
    0.68
     Airborne
    0.68
     发布
    0.67
     parfum
    0.66
    Activations Density 0.026%

    No Known Activations