© 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. 66662
    Prev
    Next
    INDEX
    Explanations

    under positions

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

    specific concepts

    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
     d
    0.63
    AS
    0.54
    UK
    0.52
     a
    0.50
    and
    0.48
     J
    0.48
    MI
    0.48
     V
    0.47
    aj
    0.47
     D
    0.47
    POSITIVE LOGITS
    iagn
    0.50
    initions
    0.49
    の関係
    0.47
     செயல்பா
    0.46
     Fahrzeug
    0.46
    ﻬ
    0.46
    肺炎
    0.45
    istoire
    0.45
    λεσμα
    0.45
    nment
    0.44
    Activations Density 0.001%

    No Known Activations