© 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. 3033
    Prev
    Next
    INDEX
    Explanations

    reserved or syntax elements

    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
     buttercream
    -0.76
    ysen
    -0.71
    َر
    -0.68
    صال
    -0.68
    िका
    -0.68
    banda
    -0.68
    ducted
    -0.67
    entia
    -0.66
    perten
    -0.65
    看向
    -0.65
    POSITIVE LOGITS
     pg
    0.71
     ό
    0.71
     peace
    0.68
     каранда
    0.68
    书记
    0.68
     weakly
    0.63
     Emin
    0.62
    一手
    0.60
    esie
    0.60
     sage
    0.60
    Activations Density 0.045%

    No Known Activations