© 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. 40398
    Prev
    Next
    INDEX
    Explanations

    services, distance, use

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

    required for processes

    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
     R
    0.63
     The
    0.54
     Establishing
    0.53
     Steady
    0.52
     Establish
    0.51
     Explo
    0.51
     Stead
    0.51
     Quin
    0.50
     E
    0.50
     Defence
    0.49
    POSITIVE LOGITS
     پارک
    0.58
     መንገድ
    0.54
     ć
    0.53
     개의
    0.53
     pétales
    0.51
    diameter
    0.51
    ম্‌
    0.51
    rij
    0.50
    ühlt
    0.50
     diamètre
    0.50
    Activations Density 0.000%

    No Known Activations