© 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. 1904
    Prev
    Next
    INDEX
    Explanations

    cat

    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
    aient
    1.16
    т
    1.11
    р
    1.11
    いる
    1.09
    ますが
    1.09
    िल
    1.08
    ર
    1.07
    DE
    1.06
    ರೆ
    1.06
    बी
    1.05
    POSITIVE LOGITS
    슨
    1.20
     tenets
    1.14
    ar
    1.13
    loid
    1.12
    kali
    1.12
    boxyl
    1.10
    ại
    1.08
    fois
    1.05
    stown
    1.05
    ad
    1.04
    Activations Density 0.117%

    No Known Activations