© 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. 169671
    Prev
    Next
    INDEX
    Explanations

    Agreement hereby

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

    simple to understand and implement

    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
     recruit
    0.47
     tedes
    0.46
     venue
    0.46
     barbers
    0.44
     lexical
    0.43
     slay
    0.42
    ﻖ
    0.42
     museum
    0.42
     Técn
    0.42
     librarian
    0.42
    POSITIVE LOGITS
     свое
    0.54
    ний
    0.44
     своем
    0.42
    芴
    0.41
    ewater
    0.40
     swoich
    0.40
     Norweg
    0.40
     свого
    0.40
    elu
    0.40
     எண்ணிக்க
    0.40
    Activations Density 0.001%

    No Known Activations