© 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. 196713
    Prev
    Next
    INDEX
    Explanations

    announcements and advertising

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

    intimacy, woman, designed, install, plants

    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
     رابطه
    0.50
     موضوع
    0.47
     بين
    0.46
     కాల
    0.46
     بعض
    0.45
    ﻮ
    0.45
     مسائل
    0.45
     acupuncture
    0.44
     ل
    0.44
     ئ
    0.44
    POSITIVE LOGITS
    Questo
    0.46
    Созда
    0.44
    <0x80>
    0.43
    nés
    0.43
    ectonic
    0.43
    lumin
    0.42
    âte
    0.42
    гим
    0.42
    ąd
    0.42
    arrants
    0.42
    Activations Density 0.001%

    No Known Activations