© 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. 22-GEMMASCOPE-RES-131K
    7. 72824
    Prev
    Next
    INDEX
    Explanations

    engine or Engine parts

    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_22/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
    “
    -3.06
    栳
    -3.05
    ⡑
    -2.75
     باسلام
    -2.45
    and
    -2.45
    
    -2.44
    ’
    -2.41
     obwohl
    -2.41
     infused
    -2.38
    的很
    -2.38
    POSITIVE LOGITS
    ем
    2.25
     menghindari
    2.19
     melap
    2.19
    抉
    2.19
     transformar
    2.17
    挞
    2.16
     provocar
    2.14
    ᮣ
    2.14
    ть
    2.14
    ꞈ
    2.13
    Activations Density 0.022%

    No Known Activations