© 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. 18750
    Prev
    Next
    INDEX
    Explanations

    free followed by nouns/adjectives

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

    finding best options/context

    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
     zh
    0.48
    disco
    0.46
    sty
    0.46
    ᅥ
    0.45
     occurs
    0.45
     Plants
    0.44
     planta
    0.44
    弟子
    0.44
     diva
    0.44
    usin
    0.44
    POSITIVE LOGITS
    зне
    0.48
     оружия
    0.48
    ز
    0.47
     ആശുപത്രി
    0.44
     veineux
    0.44
    ன்
    0.43
     اعظم
    0.43
     கண்ணாடி
    0.43
    സിന്
    0.43
     विद्यु
    0.43
    Activations Density 0.000%

    No Known Activations