© 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. 1884
    Prev
    Next
    INDEX
    Explanations

    program photography

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

    computer programs consuming resources

    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
    আরও
    0.52
    নমেন্ট
    0.51
    Номер
    0.49
    ∪
    0.49
    Გ
    0.49
     आरमारा
    0.48
    跺
    0.48
    íl
    0.48
    ⊂
    0.47
    <unused682>
    0.47
    POSITIVE LOGITS
     feminist
    0.47
     elephant
    0.45
    third
    0.45
     boxing
    0.45
    degenerate
    0.43
     citizenship
    0.43
    boxing
    0.42
     cattle
    0.41
    ْب
    0.41
     meat
    0.41
    Activations Density 0.000%

    No Known Activations