© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7517
    Prev
    Next
    INDEX
    Explanations

    scorching, searing, blistering

    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
    geſ
    -2.53
    ペーン
    -2.39
    ﮩ
    -2.30
    ￬
    -2.20
    棪
    -2.17
    zeugen
    -2.17
    ндарт
    -2.16
    莚
    -2.13
    
    -2.13
     éditoriale
    -2.13
    POSITIVE LOGITS
    ↵
    4.22
     —
    2.28
     incredibly
    2.22
    ’
    2.17
    }
    2.17
     I
    2.16
     my
    2.13
    ቷ
    2.11
     relentless
    2.09
     principalmente
    2.08
    Activations Density 0.007%

    No Known Activations