© 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. 8375
    Prev
    Next
    INDEX
    Explanations

    punctuation and mixed languages

    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
    ς
    1.09
    s
    1.08
    sı
    1.05
    lara
    0.99
    lardan
    0.93
    sail
    0.89
    ים
    0.86
    sene
    0.85
    CH
    0.84
    soldiers
    0.82
    POSITIVE LOGITS
     whereabouts
    0.80
    on
    0.72
    ].”
    0.71
    礪
    0.70
     kudos
    0.69
    ]<
    0.68
     indicato
    0.68
     ”
    0.67
    ২৮
    0.65
    つけて
    0.65
    Activations Density 1.621%

    No Known Activations