© 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. 10-GEMMASCOPE-RES-131K
    7. 67202
    Prev
    Next
    INDEX
    Explanations

    frequently + action/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
     decidedly
    -2.98
     secluded
    -2.88
     superb
    -2.83
     marvelous
    -2.81
            
    -2.78
    蠖
    -2.73
    ᚔ
    -2.73
     splendid
    -2.73
    珵
    -2.64
     delightfully
    -2.59
    POSITIVE LOGITS
     gives
    2.75
    get
    2.72
    ஂ
    2.72
    鹮
    2.72
     provides
    2.67
     火鍋
    2.66
     sizeable
    2.55
     Following
    2.53
    ～。
    2.52
     makes
    2.50
    Activations Density 0.009%

    No Known Activations