© 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. 8194
    Prev
    Next
    INDEX
    Explanations

    <start_of_turn>

    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
     fleste
    0.80
    ✶
    0.78
    <end_of_turn>
    0.73
    infini
    0.73
    🪁
    0.73
     incite
    0.72
     Aesthetics
    0.72
     tặng
    0.71
    ลล์
    0.71
     一个
    0.70
    POSITIVE LOGITS
    ੀ
    1.06
    я
    1.02
    у
    0.99
    𝓾
    0.98
    ist
    0.96
    en
    0.93
    ל
    0.92
    િ
    0.91
    or
    0.91
    ر
    0.90
    Activations Density 0.171%

    No Known Activations