© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64634
    Prev
    Next
    INDEX
    Explanations

    Indian Larry, ace Casey, Home Page, Blackberry

    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
    meler
    -0.71
     Inst
    -0.70
    про
    -0.70
    𝘺
    -0.69
    lippe
    -0.69
    MINUS
    -0.68
    vue
    -0.67
     BL
    -0.66
     propiedades
    -0.66
     То
    -0.65
    POSITIVE LOGITS
     serons
    0.80
    īb
    0.77
     sense
    0.75
    userRole
    0.73
    ränken
    0.72
    Kirchen
    0.72
    aster
    0.71
     Balas
    0.70
    ську
    0.70
    syntax
    0.70
    Activations Density 0.012%

    No Known Activations