© 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. 184461
    Prev
    Next
    INDEX
    Explanations

    road to

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

    analyzing malware and compiled programs

    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
     Chap
    0.45
     writs
    0.45
     aDict
    0.45
     jugadores
    0.45
    न्यास
    0.45
    RAFT
    0.44
    ફ
    0.44
     map
    0.44
    l
    0.44
     quill
    0.44
    POSITIVE LOGITS
    ၼ်
    0.44
    鉄
    0.44
    archiw
    0.41
    睞
    0.41
    imerk
    0.40
    吃飯
    0.40
    爣
    0.40
    वणे
    0.40
    ercicio
    0.39
    法施行令
    0.39
    Activations Density 0.000%

    No Known Activations