© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 20423
    Prev
    Next
    INDEX
    Explanations

    some/any quantifiers

    np_acts-logits-general · gemini-2.5-flash-lite

    trust region optimization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -
    0.54
    ’
    0.46
    <0xB0>
    0.44
    thel
    0.42
    cout
    0.42
    urry
    0.42
    tim
    0.42
     শ্রম
    0.41
    ,
    0.41
    rn
    0.41
    POSITIVE LOGITS
     algún
    0.54
     राग
    0.54
     alguno
    0.52
     mencionados
    0.52
     algum
    0.51
     jakieś
    0.51
     ocorre
    0.50
     bija
    0.50
     jakiś
    0.48
     alguma
    0.47
    Activations Density 0.000%

    No Known Activations