© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 8585
    Prev
    Next
    INDEX
    Explanations

    #1 rankings and top universities

    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_40_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
     బహి
    0.41
    ற்காக
    0.40
    rierung
    0.39
     carrière
    0.39
    ঙালি
    0.38
    spannung
    0.37
    inderung
    0.37
    梶
    0.37
     baz
    0.37
    Egyptian
    0.37
    POSITIVE LOGITS
     rankings
    0.90
     Rankings
    0.79
     ranking
    0.76
     ranked
    0.73
     Top
    0.70
     nation
    0.69
    ranked
    0.69
     nationally
    0.68
     Ranking
    0.66
     league
    0.64
    Activations Density 0.003%

    No Known Activations