© 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. 220088
    Prev
    Next
    INDEX
    Explanations

    submit under

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

    function change energy

    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
     secrets
    0.48
    jima
    0.47
     coffers
    0.47
     cadeaux
    0.47
     goodies
    0.46
     patrim
    0.46
    saves
    0.45
    괄
    0.45
     saves
    0.45
     χρόνο
    0.45
    POSITIVE LOGITS
    reactivex
    0.39
     irresponsible
    0.38
    ারণ
    0.38
    Objective
    0.38
     polyd
    0.38
     Gerd
    0.38
     Tn
    0.38
     Esch
    0.38
     его
    0.37
    Section
    0.37
    Activations Density 0.000%

    No Known Activations