© 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. 149225
    Prev
    Next
    INDEX
    Explanations

    archive, women, administrative, cheap, honors, flow

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

    understanding technical or programming concepts

    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
     міся
    0.56
    聸
    0.55
     выражение
    0.53
     брак
    0.49
     도와
    0.49
     фрук
    0.47
     βο
    0.46
     її
    0.45
     τὰ
    0.45
    对待
    0.45
    POSITIVE LOGITS
    -
    0.70
    rk
    0.48
    tre
    0.47
     kontrol
    0.47
    tir
    0.46
    -(-
    0.46
    NE
    0.46
    landı
    0.46
    ls
    0.46
    CI
    0.45
    Activations Density 0.001%

    No Known Activations