© 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. 202539
    Prev
    Next
    INDEX
    Explanations

    Russia, scanner, Getty

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

    `Leo`, `started`

    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
    ２
    0.53
    大きさ
    0.52
    ３
    0.49
    薷
    0.49
    変換
    0.48
    િય
    0.48
    誂
    0.47
    വയ
    0.47
    橦
    0.47
    жээ
    0.46
    POSITIVE LOGITS
     DH
    0.46
    eu
    0.46
     liters
    0.44
     assayed
    0.44
    asse
    0.44
     radiative
    0.44
     stretches
    0.43
    aut
    0.43
     bunkers
    0.43
     nanotubes
    0.43
    Activations Density 0.001%

    No Known Activations