© 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. 154590
    Prev
    Next
    INDEX
    Explanations

    related crap, rogue, Subject Navigate, piano sheet, without being

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

    fine-tuned LLaMA model

    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
     suite
    0.51
    Ἡ
    0.44
     disguise
    0.42
    ត្រ
    0.42
     salto
    0.42
     parad
    0.42
     Suite
    0.42
     connexion
    0.41
    [
    0.41
    中古
    0.41
    POSITIVE LOGITS
    эм
    0.50
    ottesville
    0.47
    ולי
    0.47
     항목
    0.47
     กําลัง
    0.47
    ıyordu
    0.47
    ExpNow
    0.46
    ভেল
    0.46
    ಿಗಳ
    0.46
    gF
    0.46
    Activations Density 0.000%

    No Known Activations