Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 6403
    Prev
    Next
    INDEX
    Explanations

    links and urls

    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
     మధ్య
    0.46
     Elektrokhimiya
    0.46
     collided
    0.43
     mineralization
    0.43
     mischievous
    0.43
     অনুপ্রবেশ
    0.43
     hemodynamic
    0.42
    ))_{
    0.42
    ⟣
    0.41
    譞
    0.41
    POSITIVE LOGITS
    https
    0.48
     https
    0.45
    pp
    0.43
    에
    0.43
    true
    0.41
     doc
    0.41
    println
    0.41
    her
    0.40
    the
    0.40
     authorities
    0.39
    Activations Density 0.000%

    No Known Activations