© 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. 16306
    Prev
    Next
    INDEX
    Explanations

    language alternatives

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

    logical or choices

    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
    ↵
    0.33
     ದೇಹ
    0.31
     murderous
    0.31
    とその
    0.30
     destruction
    0.29
     tissues
    0.28
     తన
    0.28
    했던
    0.28
     }
    0.27
     त्याची
    0.27
    POSITIVE LOGITS
     veya
    0.68
     அல்லது
    0.62
     અથવા
    0.62
     или
    0.61
     অথবা
    0.61
     किंवा
    0.57
     ಅಥವಾ
    0.56
    หรือ
    0.54
     లేదా
    0.52
     hoặc
    0.51
    Activations Density 0.000%

    No Known Activations