© 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. 6567
    Prev
    Next
    INDEX
    Explanations

    AI, marketing, politics, software terms

    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
    。
    0.72
    Lecture
    0.66
    [\
    0.66
    或
    0.65
    ，
    0.64
     the
    0.64
     because
    0.62
    Machine
    0.62
    (?
    0.62
    ।
    0.62
    POSITIVE LOGITS
     arrêter
    0.73
     boutiques
    0.65
     liens
    0.64
     deities
    0.64
     tradisional
    0.63
     rappers
    0.62
     statistik
    0.62
     traditionnel
    0.62
     secondaires
    0.61
     próprias
    0.61
    Activations Density 0.037%

    No Known Activations