© 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. 172224
    Prev
    Next
    INDEX
    Explanations

    harm a nursing baby

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

    difference and contrast

    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
    電池
    0.50
    遊戲
    0.47
    يع
    0.45
    في
    0.44
    يد
    0.43
    你不
    0.43
    ಶ್ಯ
    0.43
    센
    0.43
     ماش
    0.42
     علاج
    0.42
    POSITIVE LOGITS
     どれ
    0.53
    prot
    0.52
     continuum
    0.50
     conforme
    0.50
     compat
    0.49
     différent
    0.49
     旧
    0.49
     difer
    0.48
     farklı
    0.48
     continuité
    0.48
    Activations Density 0.000%

    No Known Activations