© 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. 12-GEMMASCOPE-2-RES-262K
    7. 5963
    Prev
    Next
    INDEX
    Explanations

    at least

    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
     tornando
    0.75
     causando
    0.66
     faisant
    0.65
     fácil
    0.63
     magní
    0.62
     când
    0.61
     również
    0.60
    و
    0.60
     referente
    0.60
     véritable
    0.59
    POSITIVE LOGITS
    pole
    0.74
    з
    0.67
    тный
    0.64
    betrieb
    0.64
    messer
    0.64
    тные
    0.62
    ication
    0.61
    哟
    0.61
    с
    0.59
    sport
    0.58
    Activations Density 0.012%

    No Known Activations