© 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. 13954
    Prev
    Next
    INDEX
    Explanations

    author names after by

    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
    i
    0.53
    f
    0.47
    @
    0.46
    0
    0.45
    pe
    0.44
    1
    0.44
    Am
    0.43
    @{
    0.43
    Í
    0.43
    CSS
    0.41
    POSITIVE LOGITS
    竰
    0.48
     عبد
    0.45
     hören
    0.44
    㫣
    0.44
     Rajiv
    0.43
    喡
    0.43
     നാ
    0.42
     duckys
    0.42
    㸽
    0.42
     scolaire
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.