© 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. 77538
    Prev
    Next
    INDEX
    Explanations

    about product and suppliers

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

    swapped = false

    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
    🦳
    0.52
    blau
    0.52
     tenéis
    0.49
    ද
    0.47
     ОС
    0.47
     élytres
    0.47
    animations
    0.47
     ਨੇ
    0.46
     पढ़ाने
    0.46
    й
    0.46
    POSITIVE LOGITS
     بگیر
    0.42
    ذیر
    0.41
     Crossroads
    0.41
    یم
    0.40
    ুরে
    0.40
    cond
    0.39
    둣
    0.39
     with
    0.38
    初めて
    0.38
    二百
    0.38
    Activations Density 0.000%

    No Known Activations