© 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. 22-GEMMASCOPE-RES-131K
    7. 70929
    Prev
    Next
    INDEX
    Explanations

    how to write

    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
    ’
    -4.69
    {
    -3.63
    —
    -2.78
    苤
    -2.58
    تیجه
    -2.58
    \
    -2.52
    "
    -2.50
    ………
    -2.50
    ]
    -2.44
    已经有
    -2.36
    POSITIVE LOGITS
    诳
    2.63
    悒
    2.59
    
    2.48
    
    2.48
    甶
    2.36
     ハロウィン
    2.28
    謇
    2.27
     золото
    2.27
    蜴
    2.25
    ᠴ
    2.25
    Activations Density 0.069%

    No Known Activations