© 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. 155227
    Prev
    Next
    INDEX
    Explanations

    locate, credible, CVT, switch, opinion, long

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

    evolve physically, rejected, paper, triene

    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
    _
    0.49
    *
    0.46
     pthread
    0.46
    OG
    0.44
    MM
    0.44
     _
    0.43
     MM
    0.41
    ቆዳ
    0.41
     maim
    0.41
     mm
    0.40
    POSITIVE LOGITS
     coração
    0.53
    र्ख
    0.51
     Komitet
    0.50
     ब्लाइंड
    0.49
     ولوبی
    0.49
    otropic
    0.49
    মালা
    0.48
    ać
    0.48
    ड़ियां
    0.48
    blum
    0.48
    Activations Density 0.000%

    No Known Activations