© 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. 78408
    Prev
    Next
    INDEX
    Explanations

    steelmaking and metallurgy

    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
    警方
    -0.79
    DOCTOR
    -0.73
     ребенок
    -0.73
    alfa
    -0.71
     dziecko
    -0.71
    Iron
    -0.70
     washer
    -0.69
     hour
    -0.69
    сте
    -0.69
    市
    -0.69
    POSITIVE LOGITS
    padu
    0.81
     ladle
    0.79
     Prakash
    0.73
    dusty
    0.72
     curar
    0.71
    geolocation
    0.71
    Caster
    0.71
    blooming
    0.69
    Tav
    0.69
    溝通
    0.68
    Activations Density 0.028%

    No Known Activations