© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3408
    Prev
    Next
    INDEX
    Explanations

    importantly, according, arguably, dare

    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
    ق
    2.23
    zelfde
    2.20
    ى
    2.11
    ان
    2.08
    ר
    1.95
    هُ
    1.91
    ת
    1.80
    id
    1.72
    ли
    1.70
    व
    1.65
    POSITIVE LOGITS
    THING
    1.67
    抑制
    1.60
    美国
    1.47
    기
    1.46
    koliko
    1.45
    łod
    1.44
    rugada
    1.44
    まつ
    1.43
    ో
    1.43
    璜
    1.43
    Activations Density 0.117%

    No Known Activations