© 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. 7983
    Prev
    Next
    INDEX
    Explanations

    keywords at start of phrase

    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
    lar
    1.31
    ৩২
    1.22
    ur
    1.21
    3
    1.21
    5
    1.20
    。
    1.14
    ilidad
    1.13
    anja
    1.10
    ul
    1.09
    9
    1.08
    POSITIVE LOGITS
     assassin
    1.82
    ória
    1.38
     attaqu
    1.34
    𝚈
    1.30
     améliorer
    1.28
     Até
    1.28
     représenter
    1.28
    𝚢
    1.27
    𝙲
    1.27
     voltou
    1.27
    Activations Density 0.021%

    No Known Activations