© 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. 85356
    Prev
    Next
    INDEX
    Explanations

    console.related actions and entities

    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
    敺
    -2.84
     unſ
    -2.63
    푏
    -2.39
     Instead
    -2.33
    纡
    -2.31
    
    -2.31
    纐
    -2.30
     meravigli
    -2.30
     illustrazione
    -2.28
     Its
    -2.22
    POSITIVE LOGITS
    \
    3.27
    –
    2.98
    B
    2.41
    With
    2.19
    to
    2.17
    sizeCache
    2.16
    ｘ
    2.16
    A
    2.14
    ﾛ
    2.13
    涐
    2.13
    Activations Density 0.010%

    No Known Activations