© 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-16K
    7. 5625
    Prev
    Next
    INDEX
    Explanations

    instructions, steps, numbered lists

    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_16k_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
    ቒ
    0.31
    ulaire
    0.29
    ]-\
    0.28
    ewną
    0.28
     VCO
    0.28
     Vig
    0.27
     Ventures
    0.27
    arya
    0.27
     சென்ற
    0.27
     ($\
    0.27
    POSITIVE LOGITS
     charters
    0.31
     espécie
    0.31
     weaves
    0.30
     breeds
    0.29
    來說
    0.29
    总是
    0.29
     apparently
    0.28
     markets
    0.28
     lanes
    0.28
    那麼
    0.27
    Activations Density 0.142%

    No Known Activations