© 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. 123164
    Prev
    Next
    INDEX
    Explanations

    specialized technical terms

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

    fetishistic, atropine, computer, marionette, cooling

    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
    ník
    0.53
     چاہی
    0.50
    łek
    0.48
    ݨ
    0.48
    sí
    0.47
    ⚛
    0.46
    出来
    0.45
     Seab
    0.45
    㪇
    0.45
    oğlu
    0.43
    POSITIVE LOGITS
     amps
    0.53
     criticizing
    0.47
     विशेषज्ञों
    0.46
     பாஜக
    0.44
     amyg
    0.44
     सीआरपीएफ
    0.44
     inflicting
    0.43
     analyzers
    0.42
    भाजपा
    0.42
     analyzes
    0.41
    Activations Density 0.000%

    No Known Activations