© 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. 44419
    Prev
    Next
    INDEX
    Explanations

    device identifiers and descriptions

    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
    硨
    -1.91
    咻
    -1.86
    ي
    -1.84
    왁
    -1.80
     '
    -1.80
     می‌توان
    -1.78
    C
    -1.78
     endorsing
    -1.75
    or
    -1.75
     intensively
    -1.74
    POSITIVE LOGITS
     gastar
    2.09
    Here
    2.06
     confiar
    2.02
     กับ
    2.00
     здесь
    1.96
     devices
    1.92
     conservar
    1.91
     experimentar
    1.91
    .’
    1.86
     adaptar
    1.84
    Activations Density 0.054%

    No Known Activations