© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 32115
    Prev
    Next
    INDEX
    Explanations

    mammography, identities, hair, managers, namely, bladder, humans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ках
    0.86
     muertos
    0.82
     kilomètres
    0.81
     marchés
    0.79
    ير
    0.78
    눕
    0.77
     côtes
    0.76
    пи
    0.76
    لس
    0.76
     autre
    0.76
    POSITIVE LOGITS
    r
    0.94
    t
    0.90
    n
    0.88
    ta
    0.85
    od
    0.83
    tu
    0.79
    d
    0.79
    conditional
    0.77
    alion
    0.75
     cask
    0.75
    Activations Density 0.000%

    No Known Activations