© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 36067
    Prev
    Next
    INDEX
    Explanations

    framing, scans, taste, claim, messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    ៈ
    0.62
     WorldCat
    0.47
     பதி
    0.44
    imgur
    0.44
    ebay
    0.44
    ешь
    0.43
    idyl
    0.43
    emn
    0.43
    ដល់
    0.43
    ontaneous
    0.41
    POSITIVE LOGITS
     avenida
    0.54
     água
    0.51
     adjourn
    0.49
     dimensión
    0.49
    Ｕ
    0.48
     figuras
    0.48
     locaux
    0.47
    루
    0.47
     adjour
    0.46
    Основ
    0.46
    Activations Density 0.002%

    No Known Activations