© 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. 8102
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    in
    1.91
    on
    1.48
    h
    1.48
    og
    1.47
    this
    1.47
    for
    1.43
     to
    1.39
    t
    1.36
     for
    1.28
    ier
    1.27
    POSITIVE LOGITS
     möj
    1.54
     zapewnia
    1.49
     décrites
    1.48
     vært
    1.44
     fornisce
    1.42
     menciona
    1.41
     placées
    1.39
     essere
    1.37
     utilizza
    1.37
     tienes
    1.35
    Activations Density 0.061%

    No Known Activations