© 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. 48823
    Prev
    Next
    INDEX
    Explanations

    lasts about

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

    shimmering pink silk

    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
     kunst
    0.48
     do
    0.46
     zast
    0.46
    ou
    0.45
     e
    0.45
     deuterium
    0.44
    unternehmen
    0.44
     acoustic
    0.43
     substitutions
    0.43
     uz
    0.43
    POSITIVE LOGITS
    лла
    0.52
    মস
    0.52
    阶段
    0.48
    קה
    0.47
    だろう
    0.47
     tossed
    0.45
    画
    0.45
    함
    0.45
    は見
    0.44
     propelled
    0.44
    Activations Density 0.000%

    No Known Activations