© 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. 160905
    Prev
    Next
    INDEX
    Explanations

    month, route, ice, gem, schools, piece

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

    emojis and abbreviations

    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
    PageComponent
    0.47
     bicarbon
    0.46
     Dernière
    0.45
    }\
    0.45
    comend
    0.44
     capitalise
    0.44
    }
    0.44
    Communications
    0.44
     carbonates
    0.43
    pportun
    0.43
    POSITIVE LOGITS
     Kisi
    0.50
     Kinn
    0.49
     توس
    0.47
    ش
    0.47
    athin
    0.47
     جس
    0.45
    πό
    0.45
    ayanti
    0.45
    gak
    0.45
     pesso
    0.44
    Activations Density 0.000%

    No Known Activations