© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67926
    Prev
    Next
    INDEX
    Explanations

    technical documentation and code

    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_22/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
     (
    -1.79
    Ⅳ
    -1.34
    Ѕ
    -1.27
    魔女
    -1.26
    EdgeInsets
    -1.24
    elsif
    -1.23
     capot
    -1.22
    ∽
    -1.20
    
    -1.18
    ция
    -1.17
    POSITIVE LOGITS
     and
    1.52
    ↵↵
    1.45
     almeno
    1.30
     erschienen
    1.27
    Xar
    1.21
    ませて
    1.20
     letzten
    1.20
     (!__
    1.20
     such
    1.17
     gehörte
    1.17
    Activations Density 0.000%

    No Known Activations