© 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
    3. Gemma-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 3424
    Prev
    Next
    INDEX
    Explanations

    government intervention or pressure

    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_24_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
     (
    0.66
     சற்று
    0.64
     somewhat
    0.63
     nějak
    0.63
    ちょっと
    0.60
     slightly
    0.58
     หรือ
    0.57
     பகுதியில்
    0.57
     of
    0.56
     ちょっと
    0.56
    POSITIVE LOGITS
    これからも
    0.59
     kontinuier
    0.55
     constamment
    0.55
    ノール
    0.53
     continuamente
    0.52
    歉
    0.51
     যতদিন
    0.50
    novu
    0.50
     continually
    0.49
    不断
    0.49
    Activations Density 0.002%

    No Known Activations