© 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. 3636
    Prev
    Next
    INDEX
    Explanations

    initialization `=`

    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
    ág
    1.06
    ím
    1.04
    いずれ
    1.02
    ős
    0.96
    íme
    0.95
    резать
    0.91
    ự
    0.89
    சையில்
    0.89
    ми
    0.88
    ла
    0.88
    POSITIVE LOGITS
    e
    1.11
    c
    1.09
    en
    0.98
    el
    0.95
    m
    0.95
    a
    0.95
    b
    0.91
     aptly
    0.89
    d
    0.88
     Straßen
    0.82
    Activations Density 0.359%

    No Known Activations