© 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. 73326
    Prev
    Next
    INDEX
    Explanations

    TF or tf abbreviations

    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
    '
    -2.36
     They
    -2.31
    ⁛
    -2.13
    ſelf
    -2.08
    contd
    -2.06
    骉
    -2.05
     controlada
    -2.03
    </h1>
    -2.02
    先是
    -2.00
    ⑊
    -2.00
    POSITIVE LOGITS
    ING
    2.64
     they
    2.63
     perpet
    2.34
    ive
    2.34
     said
    2.31
    k
    2.30
    after
    2.25
    f
    2.20
    If
    2.08
    of
    2.06
    Activations Density 0.010%

    No Known Activations