© 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. 128379
    Prev
    Next
    INDEX
    Explanations

    doubtful or questionable quality

    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
     όταν
    -2.73
    følge
    -2.66
    ophageal
    -2.63
    閹
    -2.56
     ajustar
    -2.56
     provocado
    -2.53
     個室
    -2.48
    identifikasi
    -2.48
     When
    -2.47
    Ⲉ
    -2.47
    POSITIVE LOGITS
    ↵↵
    4.31
    ↵
    3.78
     —
    3.23
    $
    3.09
    -
    2.92
    ‘
    2.84
    ER
    2.77
     –
    2.64
     impec
    2.64
    AN
    2.63
    Activations Density 0.002%

    No Known Activations