© 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. 9604
    Prev
    Next
    INDEX
    Explanations

    snow, blower, shovel, storm

    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
    G
    -3.03
            
    -2.91
    d
    -2.55
    U
    -2.55
    A
    -2.48
    S
    -2.39
    0
    -2.30
    F
    -2.28
    ؟
    -2.27
    E
    -2.22
    POSITIVE LOGITS
    <bos>
    2.20
     was
    2.17
    𓐍
    2.09
     ältere
    2.03
     滅
    2.03
    韃
    2.00
     You
    1.98
    眩
    1.97
    
    1.97
    磲
    1.92
    Activations Density 0.005%

    No Known Activations