Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 1663
    Prev
    Next
    INDEX
    Explanations

    having a

    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_16k_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
    ال
    1.73
    ки
    1.51
    á
    1.44
    は何
    1.42
     impro
    1.30
    ти
    1.29
    はこの
    1.28
    of
    1.27
    လုံး
    1.24
    to
    1.23
    POSITIVE LOGITS
    y
    1.95
     возможность
    1.90
    ي
    1.77
    ar
    1.70
     foresight
    1.65
    dock
    1.63
    pflicht
    1.63
    fors
    1.57
    gers
    1.56
    uk
    1.55
    Activations Density 0.380%

    No Known Activations