© 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. 8103
    Prev
    Next
    INDEX
    Explanations

    hit on / hitting

    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
    t
    3.95
    tional
    2.91
    ம்
    2.83
    y
    2.70
    d
    2.59
    ture
    2.52
    tR
    2.36
    و
    2.34
    지
    2.34
    ک
    2.33
    POSITIVE LOGITS
    एस
    2.41
    νο
    1.98
    е
    1.81
    нодоро
    1.80
    ्रा
    1.76
    ters
    1.75
    ES
    1.74
    gerald
    1.70
    为止
    1.70
    ﾞ
    1.66
    Activations Density 0.085%

    No Known Activations