© 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. 166132
    Prev
    Next
    INDEX
    Explanations

    inspection, analysis, also

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

    taking resources, hold items, prohibits laws

    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
     Fermi
    0.46
    चारी
    0.41
     quinine
    0.39
     chubby
    0.39
     Aldrich
    0.38
    嗲
    0.38
     thiaz
    0.37
     Laksh
    0.37
     laughing
    0.37
    缭
    0.37
    POSITIVE LOGITS
     również
    0.47
    aujourd
    0.45
     trabalh
    0.42
    തായ
    0.41
    ahaan
    0.40
     أيضاً
    0.40
     pracov
    0.39
     travaille
    0.39
    astics
    0.39
     stále
    0.39
    Activations Density 0.000%

    No Known Activations