© 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. 10-GEMMASCOPE-RES-131K
    7. 1142
    Prev
    Next
    INDEX
    Explanations

    forceful passage or removal

    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
    }
    -2.88
    er
    -2.63
    at
    -2.58
    it
    -2.47
    ad
    -2.42
     esperado
    -2.31
    ar
    -2.28
    ⸫
    -2.25
    lo
    -2.25
    一部分
    -2.23
    POSITIVE LOGITS
    砹
    2.70
    釙
    2.50
    ⡯
    2.38
     夜景
    2.36
    
    2.34
    錞
    2.33
    拶
    2.25
    幃
    2.19
    ⻬
    2.19
    étaire
    2.16
    Activations Density 0.001%

    No Known Activations