© 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. 86447
    Prev
    Next
    INDEX
    Explanations

    steel, equity, packaging

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

    driver relies

    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
    مجھے
    0.52
     certes
    0.51
     fertiliser
    0.48
    入場
    0.48
     hefyd
    0.48
    屎
    0.48
     tornare
    0.47
     retorn
    0.46
    の人
    0.46
    ӟ
    0.46
    POSITIVE LOGITS
    0.58
     ResultSet
    0.56
     Equity
    0.55
     Объ
    0.55
    ing
    0.53
     (
    0.52
     Property
    0.52
     State
    0.52
    af
    0.51
     Packaging
    0.51
    Activations Density 0.002%

    No Known Activations