© 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. 63298
    Prev
    Next
    INDEX
    Explanations

    classification systems

    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
    ४
    -1.10
     Anyway
    -0.99
    ᵴ
    -0.98
    Spieler
    -0.96
     cubre
    -0.95
    tolsó
    -0.94
     Honestly
    -0.94
    blick
    -0.93
    ТЕЛЬ
    -0.92
    AutoresizingMask
    -0.92
    POSITIVE LOGITS
     Classification
    1.58
     classification
    1.31
    at
    1.28
     according
    1.27
    Classification
    1.25
     classi
    1.23
    id
    1.22
     Classi
    1.14
    of
    1.13
     Clas
    1.12
    Activations Density 0.013%

    No Known Activations