© 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. 31531
    Prev
    Next
    INDEX
    Explanations

    songwriting

    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
    f
    2.03
    id
    1.98
    ore
    1.95
    ol
    1.91
    ist
    1.84
    us
    1.82
    った
    1.80
    ag
    1.80
    cenia
    1.77
    un
    1.73
    POSITIVE LOGITS
    ت
    2.05
    ан
    2.03
     lương
    1.96
     paramètres
    1.91
     distr
    1.91
     phương
    1.91
     Stopwatch
    1.88
     Swal
    1.88
    ари
    1.84
    픈
    1.84
    Activations Density 0.014%

    No Known Activations