© 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. 80670
    Prev
    Next
    INDEX
    Explanations

    same as

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

    same

    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
     adegu
    0.48
     अवधारणा
    0.47
     edific
    0.46
     ഞ
    0.46
     obstante
    0.45
     ہونا
    0.45
    чайно
    0.45
    ಗ
    0.45
     garg
    0.43
     רא
    0.43
    POSITIVE LOGITS
    t
    0.69
    hton
    0.57
     you
    0.54
    au
    0.54
    reg
    0.54
    alt
    0.51
    ov
    0.50
     Rong
    0.50
    tip
    0.49
    uin
    0.49
    Activations Density 0.064%

    No Known Activations