© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 8033
    Prev
    Next
    INDEX
    Explanations

    digital followed by a noun

    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_16k_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
    ا
    1.97
    ]))
    1.87
    lt
    1.84
    го
    1.80
    המ
    1.77
    ı
    1.76
    স
    1.74
    تج
    1.63
    était
    1.63
    pets
    1.62
    POSITIVE LOGITS
    <0x80>
    2.19
    gestellt
    1.89
    gown
    1.88
    裡的
    1.74
    CONN
    1.72
    wor
    1.66
     plabic
    1.66
    Ь
    1.66
    ging
    1.66
     Chiron
    1.64
    Activations Density 0.074%

    No Known Activations