© 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. 145329
    Prev
    Next
    INDEX
    Explanations

    longer description, form, time

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

    script and twitter threads

    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
    к
    0.51
     Musik
    0.45
     Sut
    0.45
    ף
    0.45
     Ut
    0.45
     Aroma
    0.45
     FormGroup
    0.45
     Anda
    0.44
    冬
    0.44
    Shut
    0.44
    POSITIVE LOGITS
    ਾਲ
    0.56
    ︹
    0.48
     hypothesize
    0.48
     পথে
    0.47
    াহিদ
    0.46
    届け
    0.45
    łą
    0.45
    を結
    0.45
    urile
    0.44
    くなる
    0.44
    Activations Density 0.000%

    No Known Activations