© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69857
    Prev
    Next
    INDEX
    Explanations

    emergency response

    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
    '
    -1.77
    </h1>
    -1.71
    Getting
    -1.54
    спользование
    -1.51
     intricate
    -1.51
     большая
    -1.49
    🧷
    -1.49
    ஏ
    -1.48
    用来
    -1.48
    ketten
    -1.48
    POSITIVE LOGITS
     promessa
    1.88
    “)
    1.84
     lampada
    1.76
    銕
    1.70
    镲
    1.67
    洐
    1.65
     envía
    1.63
    ⢫
    1.63
     detiene
    1.63
    かは
    1.61
    Activations Density 0.026%

    No Known Activations