© 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. 191565
    Prev
    Next
    INDEX
    Explanations

    Each provided transformative innovation

    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
     lest
    0.37
    assertRaises
    0.36
    龊
    0.36
    nice
    0.36
     trzeba
    0.36
     Permanente
    0.36
     (!
    0.35
     Valent
    0.35
    ायल
    0.35
     карь
    0.35
    POSITIVE LOGITS
     each
    0.54
    Each
    0.49
    各
    0.47
    㗽
    0.45
     каждой
    0.44
     transformative
    0.44
     каждого
    0.43
    鑄
    0.43
     repurchase
    0.42
     Each
    0.42
    Activations Density 0.001%

    No Known Activations