© 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. 8710
    Prev
    Next
    INDEX
    Explanations

    analogue/analog circuits and signals

    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
    ل
    2.41
    ра
    2.25
    ן
    2.06
    ा
    1.92
    ات
    1.90
    ва
    1.83
    a
    1.74
    ار
    1.71
    وینت
    1.67
    planatory
    1.66
    POSITIVE LOGITS
    TorpedoStore
    2.08
    IAN
    1.90
    おります
    1.89
     prawie
    1.82
     elke
    1.81
     romanos
    1.75
    ர்ந்த
    1.70
     suiv
    1.70
    させていただきます
    1.70
    其
    1.70
    Activations Density 0.007%

    No Known Activations