© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 44361
    Prev
    Next
    INDEX
    Explanations

    customer inquiries and service experiences

    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
    ic
    1.53
    f
    1.52
    0
    1.33
     besoins
    1.29
    m
    1.28
     Rentals
    1.20
     utilisée
    1.19
    efeller
    1.18
    id
    1.17
    il
    1.16
    POSITIVE LOGITS
     비롯
    1.28
    이라는
    1.20
    㞖
    1.11
    зва
    1.10
    ATED
    1.08
    の新
    1.08
    да
    1.07
    ലാ
    1.07
    특별시
    1.06
    ских
    1.05
    Activations Density 0.001%

    No Known Activations