© 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. 22-GEMMASCOPE-RES-131K
    7. 26883
    Prev
    Next
    INDEX
    Explanations

    proportional to or related to mathematical formulas

    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_22/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
    羮
    -1.30
    谡
    -1.29
     waarschijnlijk
    -1.24
     ovviamente
    -1.19
    romeda
    -1.18
    fotograf
    -1.17
    Ꮠ
    -1.16
     erreichte
    -1.14
     folgte
    -1.13
    richtig
    -1.13
    POSITIVE LOGITS
     of
    1.45
     (
    1.24
    k
    1.09
    (
    1.03
     part
    1.03
     if
    1.00
     in
    1.00
     despite
    1.00
     modern
    0.96
     школа
    0.95
    Activations Density 0.004%

    No Known Activations