© 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. 10-GEMMASCOPE-RES-131K
    7. 66582
    Prev
    Next
    INDEX
    Explanations

    found in location or state

    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_10/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
    archiwizowane
    -1.47
     xviii
    -1.46
     blumen
    -1.45
     stiefel
    -1.45
     devraient
    -1.42
     xvi
    -1.42
     représentant
    -1.38
    ፱
    -1.35
    裢
    -1.32
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.31
    POSITIVE LOGITS
     in
    2.25
     during
    1.80
     after
    1.71
     at
    1.68
     on
    1.65
     before
    1.63
     by
    1.59
     just
    1.59
     because
    1.57
     nestled
    1.55
    Activations Density 0.064%

    No Known Activations