Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 31282
    Prev
    Next
    INDEX
    Explanations

    viewport height `vh`

    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
    د
    2.03
    મ
    1.57
    ת
    1.48
    로는
    1.46
    क
    1.45
    дцать
    1.41
    ت
    1.39
    ದ್ದು
    1.38
    нодоро
    1.36
    ный
    1.34
    POSITIVE LOGITS
     ormai
    1.28
    cluso
    1.22
    anced
    1.21
     entfernt
    1.21
    ç
    1.21
     Singing
    1.20
     longitud
    1.19
     Produkte
    1.19
    리오
    1.19
    ach
    1.17
    Activations Density 0.005%

    No Known Activations