© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 4000
    Prev
    Next
    INDEX
    Explanations

    prefix-suffix word parts

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

    bodybuilding

    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
     of
    0.43
     de
    0.38
    ש
    0.37
     et
    0.36
     \
    0.35
     y
    0.34
     to
    0.33
     Et
    0.32
     afficher
    0.32
    of
    0.32
    POSITIVE LOGITS
    стоян
    0.35
    ORIA
    0.32
    centric
    0.32
    시대
    0.31
     उत्सा
    0.31
    බන්ධ
    0.31
     മാത്രമല്ല
    0.31
    bians
    0.30
    Mississippi
    0.30
    Ɛ
    0.30
    Activations Density 0.447%

    No Known Activations