© 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. 249556
    Prev
    Next
    INDEX
    Explanations

    phrases often preceded by terms or followed by punctuation

    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
     Whitley
    0.53
     Household
    0.52
     Private
    0.51
     Martha
    0.50
    *;
    0.47
     vice
    0.47
    hold
    0.46
     P
    0.44
     Putnam
    0.44
     Small
    0.44
    POSITIVE LOGITS
    凪
    0.52
    eraient
    0.51
    POSIX
    0.50
    ลูกค้า
    0.49
     зали
    0.48
    istiche
    0.47
     заги
    0.47
    疲れ
    0.47
    ANTES
    0.46
    அல்லாஹ்
    0.46
    Activations Density 0.000%

    No Known Activations