© 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. 30874
    Prev
    Next
    INDEX
    Explanations

    categories and sub-points

    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
     разных
    1.13
     różnych
    1.13
     ámbitos
    1.07
    いろんな
    1.05
     різних
    1.04
     различных
    1.02
    ayeva
    1.01
    薨
    1.00
     innych
    1.00
     zahlreiche
    0.99
    POSITIVE LOGITS
    1.13
     the
    1.10
     they
    1.02
     X
    0.99
     their
    0.96
    i
    0.91
    x
    0.91
    ,
    0.90
     you
    0.89
     x
    0.89
    Activations Density 0.145%

    No Known Activations