© 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. 217554
    Prev
    Next
    INDEX
    Explanations

    Nymphomaniac, monitoring, interventionist, almost, VI

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

    find ways to solve

    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
     erhältlich
    0.49
    rud
    0.47
    reck
    0.46
     limpieza
    0.46
    isit
    0.45
    jen
    0.44
     valuations
    0.44
    ǂ
    0.44
    oč
    0.43
    gener
    0.43
    POSITIVE LOGITS
     subprocess
    0.46
    ="<%=
    0.46
    、
    0.46
     predetermined
    0.45
    க்கவும்
    0.45
    ক্ষেপ
    0.44
    পদের
    0.44
    ると
    0.44
    Scale
    0.42
    Acute
    0.42
    Activations Density 0.000%

    No Known Activations