© 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-16K
    7. 1108
    Prev
    Next
    INDEX
    Explanations

    language formatting or correction

    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
     élo
    1.96
    '
    1.81
    ことにより
    1.73
    €™
    1.73
    '')
    1.72
     écriv
    1.70
    ことが多い
    1.70
    ’
    1.69
     również
    1.67
     uniquement
    1.66
    POSITIVE LOGITS
    ل
    2.16
    з
    2.09
    י
    1.88
    r
    1.75
    l
    1.70
    v
    1.63
    ज
    1.63
    ন
    1.62
    р
    1.51
    িয়ান
    1.50
    Activations Density 0.000%

    No Known Activations