© 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-262K
    7. 260
    Prev
    Next
    INDEX
    Explanations

    kingdom of

    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_262k_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
    ков
    1.98
    ୍
    1.66
     לנו
    1.59
    śmy
    1.53
     mistake
    1.52
     ومع
    1.48
     إذا
    1.45
    輌
    1.44
    と言う
    1.40
     narrative
    1.39
    POSITIVE LOGITS
    t
    4.22
    ت
    2.95
    ます
    2.75
    tä
    2.64
    tion
    2.47
    tare
    2.45
    tuk
    2.39
    tive
    2.39
    tional
    2.39
    tad
    2.36
    Activations Density 0.005%

    No Known Activations