© 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. 6691
    Prev
    Next
    INDEX
    Explanations

    jazz history, fusion, festival, music, musician

    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
    на
    1.84
    j
    1.77
    ш
    1.75
    اب
    1.70
    е
    1.70
    о
    1.66
    п
    1.66
    и
    1.64
    و
    1.62
    ні
    1.55
    POSITIVE LOGITS
    ים
    1.62
     stifle
    1.62
     thrive
    1.53
     deprive
    1.45
     denote
    1.44
     create
    1.40
     reconcile
    1.40
     scour
    1.38
     kinetics
    1.34
     withstand
    1.34
    Activations Density 0.013%

    No Known Activations