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. 1907
    Prev
    Next
    INDEX
    Explanations

    s

    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
    is
    2.58
    ar
    2.39
    v
    2.19
    ur
    2.16
    p
    2.09
    er
    2.08
    al
    2.08
    ap
    2.08
    a
    2.05
    y
    2.03
    POSITIVE LOGITS
     enkel
    1.25
     whereabouts
    1.23
     Aan
    1.20
     qur
    1.19
     Viewed
    1.18
     moderation
    1.15
    ্শন
    1.15
    UM
    1.13
     purchase
    1.12
     Wanted
    1.12
    Activations Density 0.148%

    No Known Activations