© 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. 117139
    Prev
    Next
    INDEX
    Explanations

    baseball players and teams

    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
     Branson
    -0.86
    vv
    -0.84
    𓂂
    -0.83
     глоба
    -0.82
    след
    -0.82
    HH
    -0.82
    pegawai
    -0.79
    зыв
    -0.79
     ২০১
    -0.77
     تصریح
    -0.77
    POSITIVE LOGITS
     UPI
    0.93
    Montreal
    0.86
     sacerdotes
    0.84
     jugos
    0.84
    odore
    0.84
     🤍
    0.84
     tena
    0.83
     wartime
    0.83
     Montreal
    0.82
    #:
    0.81
    Activations Density 0.051%

    No Known Activations