© 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. 40-GEMMASCOPE-2-RES-262K
    7. 211552
    Prev
    Next
    INDEX
    Explanations

    towards thedelivered weeklyleave ,Σ (xi * xiᵀ)

    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
    ’),
    0.44
    colormap
    0.42
    favicon
    0.42
    $),
    0.42
    occhi
    0.42
    䢌
    0.41
    '),
    0.41
     اکاؤن
    0.41
     শ
    0.40
     کوشش
    0.40
    POSITIVE LOGITS
    Фу
    0.41
    管
    0.40
    ప్పు
    0.38
     подой
    0.38
     ситуация
    0.36
    ត
    0.36
    物
    0.36
     warehouses
    0.35
     acel
    0.35
     swelling
    0.35
    Activations Density 0.000%

    No Known Activations