© 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. 113193
    Prev
    Next
    INDEX
    Explanations

    bl followed by suffixes

    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
    ኧ
    -3.22
    ꙮ
    -3.17
    镚
    -3.09
    崀
    -3.06
    箆
    -3.05
    霂
    -3.02
    鬟
    -2.98
    
    -2.97
    呖
    -2.89
    🪤
    -2.86
    POSITIVE LOGITS
    </strong>
    3.00
    "}}>
    2.69
    ."
    2.64
     If
    2.59
    !
    2.55
     \&
    2.47
    鬭
    2.45
    猡
    2.44
     Если
    2.42
     It
    2.41
    Activations Density 0.012%

    No Known Activations