© 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. 196127
    Prev
    Next
    INDEX
    Explanations

    when what

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

    long term implications

    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
    thousand
    0.47
     نزدیک
    0.44
    administration
    0.44
    thousands
    0.44
    different
    0.43
    :
    0.42
    Mech
    0.41
    things
    0.40
    :.
    0.40
    administrative
    0.40
    POSITIVE LOGITS
    ене
    0.48
     シン
    0.47
    ája
    0.45
    apos
    0.45
    哎
    0.43
    舆
    0.42
    ênh
    0.42
     দ
    0.42
    ાઈ
    0.42
    翁
    0.42
    Activations Density 0.000%

    No Known Activations