© 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-16K
    7. 12772
    Prev
    Next
    INDEX
    Explanations

    publishing dates

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

    code generation and function explanation

    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_16k_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
     tampoco
    0.46
     semelhantes
    0.43
     রূপে
    0.42
    For
    0.42
     отношении
    0.41
    মিও
    0.41
     kesempatan
    0.40
    {}\
    0.40
     matlab
    0.40
    áticas
    0.40
    POSITIVE LOGITS
    re
    0.43
    flows
    0.41
     Essence
    0.41
     येते
    0.41
    enters
    0.41
    flow
    0.40
    engines
    0.40
    iflix
    0.40
    journ
    0.40
    ऽ
    0.40
    Activations Density 0.000%

    No Known Activations