© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 136213
    Prev
    Next
    INDEX
    Explanations

    seasonings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vấn
    0.48
    ⵥ
    0.48
     inversión
    0.47
    ллина
    0.47
     tabuleiro
    0.46
     thérapeut
    0.46
    Jogador
    0.46
     활
    0.46
    𒆤
    0.45
    に見
    0.45
    POSITIVE LOGITS
    arding
    0.46
    cke
    0.46
    ipping
    0.45
    ming
    0.45
    ,.
    0.45
    cher
    0.44
     either
    0.44
    ale
    0.43
    bing
    0.43
    .');
    0.43
    Activations Density 0.001%

    No Known Activations