© 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. 50572
    Prev
    Next
    INDEX
    Explanations

    year since

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

    historical and current context

    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
    য়ে
    0.53
    i
    0.52
    য়ে
    0.51
    น
    0.46
    ი
    0.46
     seeing
    0.45
    ین
    0.44
     prioritise
    0.44
    n
    0.43
     SAME
    0.42
    POSITIVE LOGITS
    equilibrium
    0.54
     چهار
    0.52
     puriso
    0.52
    邛
    0.51
     dakkh
    0.51
     سريع
    0.49
    REPORT
    0.49
     모르
    0.49
     allerdings
    0.49
     mutta
    0.49
    Activations Density 0.000%

    No Known Activations