© 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. 117189
    Prev
    Next
    INDEX
    Explanations

    spirit, belief, flint, structures

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

    regex flags and syntax

    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
    ເທ
    0.51
    ールの
    0.48
    轼
    0.48
    aiset
    0.45
    ल्ले
    0.45
    લ્સ
    0.45
    することで
    0.43
    외부
    0.43
    賂
    0.43
    ље
    0.43
    POSITIVE LOGITS
     เสียง
    0.49
     สวัสดี
    0.48
     iza
    0.47
     ตาม
    0.47
     बि
    0.47
    m
    0.47
     titik
    0.46
     আপ
    0.46
    ne
    0.46
     čís
    0.46
    Activations Density 0.000%

    No Known Activations