© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 16660
    Prev
    Next
    INDEX
    Explanations

    The Invisible Architect: An Essay on Wind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (
    0.56
     \
    0.41
     =
    0.41
     {//
    0.40
     de
    0.40
     mip
    0.40
     m
    0.39
     (>
    0.38
     {
    0.38
     à
    0.38
    POSITIVE LOGITS
    надцать
    0.45
    chyné
    0.38
    reszt
    0.38
    俬
    0.38
    Alton
    0.37
    偣
    0.37
    шед
    0.36
    Ḍ
    0.36
    idcar
    0.36
    শিদ
    0.35
    Activations Density 0.238%

    No Known Activations