© 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. 71400
    Prev
    Next
    INDEX
    Explanations

    technical concepts and explanations

    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
    úblic
    0.54
    ρωση
    0.47
     repertoire
    0.46
     sexist
    0.46
    少なくとも
    0.46
    u
    0.46
     سیاسی
    0.46
     compromise
    0.45
     melancholy
    0.44
    ूर्त
    0.44
    POSITIVE LOGITS
     Erschein
    0.46
    陨
    0.44
     الذين
    0.43
     výro
    0.43
     Eli
    0.43
     Tonawanda
    0.41
     Bericht
    0.41
     část
    0.41
     chcia
    0.41
     deswegen
    0.41
    Activations Density 0.014%

    No Known Activations