© 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. 34-GEMMASCOPE-RES-131K
    7. 65190
    Prev
    Next
    INDEX
    Explanations

    hyphen or dash punctuation

    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_34/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
     of
    -1.63
     in
    -1.51
    ЧЕСКИ
    -1.47
     for
    -1.45
     役
    -1.42
     to
    -1.23
    ならでは
    -1.20
    reportWebVitals
    -1.19
     hjælpe
    -1.19
     døde
    -1.16
    POSITIVE LOGITS
     –
    7.19
     -
    6.31
     —
    5.66
     $-$
    5.09
     --
    4.81
    —
    4.38
    --
    3.67
    –
    3.59
     −
    3.52
     $-
    3.33
    Activations Density 0.870%

    No Known Activations