© 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. 129055
    Prev
    Next
    INDEX
    Explanations

    $\mathbb{R}$ notation

    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
    le
    -3.20
    This
    -2.95
    2
    -2.92
    what
    -2.73
    $
    -2.53
    al
    -2.39
    o
    -2.36
    From
    -2.34
    just
    -2.34
    is
    -2.31
    POSITIVE LOGITS
    鼍
    2.66
    ’
    2.58
    蛲
    2.50
    珦
    2.44
     constantemente
    2.36
    archiwizowane
    2.25
    鶺
    2.20
    ﮧ
    2.20
    鼉
    2.14
     Перейти
    2.09
    Activations Density 0.005%

    No Known Activations