© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 97893
    Prev
    Next
    INDEX
    Explanations

    match keyword usage

    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
     prostředí
    -1.07
    蒟
    -1.00
     amalgamation
    -0.98
    zystać
    -0.94
     Theology
    -0.94
     Estación
    -0.92
    }))
    -0.92
    忾
    -0.91
     části
    -0.90
    Split
    -0.88
    POSITIVE LOGITS
    ings
    1.21
    s
    1.10
    stick
    1.09
    ング
    1.08
    뤼
    1.07
    cing
    0.97
    n
    0.96
     any
    0.96
     our
    0.95
     Schi
    0.93
    Activations Density 0.015%

    No Known Activations