© 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. 30455
    Prev
    Next
    INDEX
    Explanations

    code and markup syntax

    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
     картин
    -0.75
    agascar
    -0.71
     Kapitel
    -0.70
    charging
    -0.69
     charging
    -0.68
     ess
    -0.66
    Connectivity
    -0.66
     lt
    -0.65
     wä
    -0.65
    titude
    -0.63
    POSITIVE LOGITS
     deles
    0.83
    sierra
    0.78
     Mush
    0.76
     govern
    0.75
     étage
    0.75
    Mush
    0.74
     prudence
    0.73
     Bored
    0.73
     tiring
    0.73
    ᚑ
    0.73
    Activations Density 0.064%

    No Known Activations