© 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. 58248
    Prev
    Next
    INDEX
    Explanations

    opening bracket/quote, followed by custom code/values

    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
     verts
    -0.72
    lectable
    -0.70
    ţă
    -0.68
    InUse
    -0.67
     הל
    -0.66
    bcrypt
    -0.65
     paris
    -0.65
    Ω
    -0.64
     gateway
    -0.64
     jailed
    -0.62
    POSITIVE LOGITS
     chauffeur
    0.81
     Shira
    0.81
    coaching
    0.79
    EventBus
    0.79
     siri
    0.74
     család
    0.73
     között
    0.73
     vzor
    0.72
     FixedUpdate
    0.71
    rind
    0.71
    Activations Density 0.032%

    No Known Activations