© 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. 41849
    Prev
    Next
    INDEX
    Explanations

    HTML paragraph tags

    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
     tampak
    0.48
    tower
    0.46
    ėtų
    0.44
    ၊
    0.43
    ᚗ
    0.43
     Shah
    0.42
     mugs
    0.42
    ਣ
    0.41
     previews
    0.41
     an
    0.40
    POSITIVE LOGITS
     copi
    0.48
    ्स
    0.47
     continuité
    0.47
     enfermed
    0.46
     አንዳንድ
    0.46
     ورحمه
    0.46
     mito
    0.46
     نكمل
    0.45
     direcion
    0.45
     прибыли
    0.45
    Activations Density 0.012%

    No Known Activations