© 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. 9323
    Prev
    Next
    INDEX
    Explanations

    static, impl, or Niche followed by related code/web terms

    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
    ru
    0.53
    htim
    0.45
    鷺
    0.44
    am
    0.44
     ਵਿੱਚ
    0.44
    bey
    0.43
    abil
    0.43
    bss
    0.43
    Eng
    0.42
    Ru
    0.42
    POSITIVE LOGITS
     discursive
    0.55
     cosmic
    0.51
     semantic
    0.50
    <unused80>
    0.49
     çev
    0.47
     canonical
    0.46
     currentNode
    0.46
     quadrupole
    0.46
     acqua
    0.46
     Cosmic
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.