© 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. 37474
    Prev
    Next
    INDEX
    Explanations

    vital records

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

    cons, ; destiny, bot, lose, weaver

    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
    io
    0.58
    u
    0.56
    nth
    0.50
    sville
    0.50
    stown
    0.50
     on
    0.49
    artis
    0.49
     estuary
    0.49
    ">
    0.48
    iget
    0.48
    POSITIVE LOGITS
    amerikanischer
    0.46
    UNK
    0.46
    佛教
    0.46
    яна
    0.44
    گ
    0.44
    ἢ
    0.44
    之道
    0.43
    蠅
    0.43
    大规模
    0.43
     നമഃ
    0.42
    Activations Density 0.000%

    No Known Activations