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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 2930
    Prev
    Next
    INDEX
    Explanations

    of following tokens

    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
    حدیث
    1.17
     Dtsch
    1.09
     appellant
    1.09
    ی
    1.08
    IE
    1.07
    i
    1.07
     Distinction
    1.06
    '
    1.05
     Dij
    1.02
    على
    1.01
    POSITIVE LOGITS
    ون
    1.27
    ingly
    1.21
    ენ
    1.12
    ната
    1.09
    en
    1.06
    nál
    1.05
    놈
    1.04
    adı
    1.03
    ವಾರ
    1.02
    ate
    1.01
    Activations Density 0.120%

    No Known Activations