© 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. 84325
    Prev
    Next
    INDEX
    Explanations

    organizations and technical terms

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

    considered to bedangerous habitconsidered smallpunishment stories

    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
     ущер
    0.54
     দ্বিত
    0.52
    徕
    0.51
    选举
    0.49
    attuale
    0.49
    ﺔ
    0.48
    material
    0.48
     দাড়
    0.46
     جعلی
    0.46
    辮
    0.46
    POSITIVE LOGITS
     (
    0.49
     asia
    0.49
     CIR
    0.48
     anastomosis
    0.48
     (=
    0.46
     Asia
    0.46
     Herm
    0.46
     meet
    0.45
     Frida
    0.44
     "."
    0.43
    Activations Density 0.001%

    No Known Activations