© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74699
    Prev
    Next
    INDEX
    Explanations

    carpeting, CCTV, acupuncture, Qt, Russian transliteration

    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
    section
    -3.25
    1
    -2.97
     The
    -2.47
    0
    -2.42
    h
    -2.28
    퐹
    -2.25
    </b>
    -2.20
     --
    -2.19
    м
    -2.08
    P
    -2.05
    POSITIVE LOGITS
    逦
    3.42
    횃
    2.70
    薷
    2.63
    褔
    2.61
    
    2.56
    餮
    2.56
    秾
    2.53
    
    2.48
    玧
    2.47
    𓆏
    2.47
    Activations Density 0.002%

    No Known Activations