© 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. 2623
    Prev
    Next
    INDEX
    Explanations

    quality and positive descriptions

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

    fetch data, uses Tailwind, represent your

    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
    ian
    0.60
    PRE
    0.48
    or
    0.47
    an
    0.47
    n
    0.47
    ul
    0.46
    io
    0.45
    Fi
    0.45
    idan
    0.45
    mest
    0.45
    POSITIVE LOGITS
     zostały
    0.51
    ෂ
    0.49
     ru
    0.49
     contained
    0.48
     mapDispatch
    0.48
     ruin
    0.46
    خر
    0.46
     Moskau
    0.46
     monitored
    0.46
     fluent
    0.46
    Activations Density 0.000%

    No Known Activations