© 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. 129048
    Prev
    Next
    INDEX
    Explanations

    technical documentation and scientific writing

    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
     However
    -2.44
     Some
    -2.28
     Now
    -2.16
     erfordert
    -2.06
     You
    -2.06
     Ultimately
    -2.03
     Anſ
    -1.99
     sebelum
    -1.98
     Certainly
    -1.98
     permita
    -1.97
    POSITIVE LOGITS
    ↵↵
    2.45
    肫
    2.31
    }
    2.14
    SuppressMessage
    2.13
    箆
    2.11
    涐
    1.91
    逦
    1.90
    大军
    1.90
     hien
    1.87
    ='".$
    1.86
    Activations Density 0.000%

    No Known Activations