© 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. 78542
    Prev
    Next
    INDEX
    Explanations

    air puff

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

    Why matters

    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
     his
    0.63
    6
    0.53
     Ke
    0.52
     May
    0.49
     Went
    0.49
     fie
    0.49
     mely
    0.49
     pers
    0.49
     gone
    0.48
     Due
    0.48
    POSITIVE LOGITS
     광고
    0.48
    콴
    0.47
    isotropic
    0.46
    aków
    0.46
    intrusion
    0.45
    corollary
    0.45
     투자
    0.45
    팰
    0.44
     اہلِ
    0.44
    േജ്
    0.44
    Activations Density 0.000%

    No Known Activations