© 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. 204563
    Prev
    Next
    INDEX
    Explanations

    frequently makes

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

    academic institutions

    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
     loosened
    0.53
     severely
    0.49
     کوڈ
    0.48
     совокуп
    0.48
     stung
    0.48
    ม
    0.48
     ఏడాది
    0.47
    mocha
    0.47
     constructively
    0.46
     ingrained
    0.46
    POSITIVE LOGITS
    iday
    0.51
    V
    0.49
    (
    0.46
    adians
    0.44
    uo
    0.44
    of
    0.43
    vc
    0.43
    yy
    0.43
    ppy
    0.42
    Translations
    0.42
    Activations Density 0.000%

    No Known Activations