© 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. 114533
    Prev
    Next
    INDEX
    Explanations

    companies, language, or size

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

    can see, for definitions, handling dynamic content

    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
     strictly
    0.52
     be
    0.51
     harmless
    0.46
    cog
    0.46
     mar
    0.45
     benign
    0.45
     i
    0.44
     worthy
    0.44
     uyg
    0.43
     cog
    0.42
    POSITIVE LOGITS
    ザー
    0.45
    萎
    0.45
    effer
    0.43
    ذاب
    0.42
     업체
    0.42
    estabelecimento
    0.42
    滁
    0.41
    عات
    0.41
    대의
    0.41
    淄
    0.41
    Activations Density 0.000%

    No Known Activations