© 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. 122427
    Prev
    Next
    INDEX
    Explanations

    home & renovation television

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

    explaining in layman's terms

    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
    }=
    0.47
    Durch
    0.45
    舊
    0.45
    個月
    0.44
    }=\
    0.44
    medio
    0.43
     Sprache
    0.43
    奐
    0.42
     সময়ে
    0.42
    Gn
    0.42
    POSITIVE LOGITS
     Interfaith
    0.46
    chman
    0.46
    ।-
    0.46
    DataItem
    0.45
     Jillian
    0.43
    et
    0.43
    सिया
    0.42
     hoodies
    0.42
    idig
    0.42
     மிரு
    0.42
    Activations Density 0.000%

    No Known Activations