© 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. 37903
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

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

    numbers and codes

    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
     Epit
    0.41
    時候
    0.41
    ጷ
    0.41
     Zou
    0.40
    })(
    0.39
    虍
    0.39
     *}
    0.39
    })-(\
    0.39
    Payout
    0.38
     Forma
    0.38
    POSITIVE LOGITS
     brightly
    0.39
    realpath
    0.39
    共有
    0.35
     themselves
    0.35
    remember
    0.35
     compart
    0.34
    IE
    0.34
     remembered
    0.34
    iels
    0.34
     literalmente
    0.34
    Activations Density 0.030%

    No Known Activations