© 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. 193547
    Prev
    Next
    INDEX
    Explanations

    ways of knowing

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

    preteen students and years old

    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
    st
    0.41
     Ritz
    0.40
    눴
    0.39
     Chancellor
    0.39
     보고
    0.39
     ทำให้
    0.39
    ভিত্তিক
    0.38
    cante
    0.38
    췄
    0.38
     French
    0.38
    POSITIVE LOGITS
     друг
    0.53
     আঁচ
    0.49
     vasculaire
    0.48
    StillWater
    0.46
     воздух
    0.46
     przyj
    0.46
     kurze
    0.45
     jaren
    0.44
    荃灣
    0.44
     bestaat
    0.44
    Activations Density 0.011%

    No Known Activations