© 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. 164569
    Prev
    Next
    INDEX
    Explanations

    action followed by specification

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

    learned based on patterns

    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
     merge
    0.47
     relinqu
    0.47
     publish
    0.46
     code
    0.45
    l
    0.45
     military
    0.43
    Script
    0.43
     Code
    0.43
    !
    0.43
     republic
    0.42
    POSITIVE LOGITS
     सांगितलं
    0.48
    يون
    0.47
    键盘
    0.46
    akul
    0.45
    酰
    0.45
     відповіда
    0.45
    锈钢
    0.44
    บริการ
    0.44
    aków
    0.43
    导演
    0.43
    Activations Density 0.002%

    No Known Activations