© 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. 84217
    Prev
    Next
    INDEX
    Explanations

    specific entities and discoveries

    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
     Kalman
    0.38
    内に
    0.38
    žno
    0.38
     tunnelling
    0.38
    塩
    0.37
    ี้ย
    0.37
     σ
    0.36
    物の
    0.36
     iniciando
    0.36
     кам
    0.35
    POSITIVE LOGITS
    Discover
    0.47
    Discovery
    0.45
    Enable
    0.42
    Gone
    0.42
    Ça
    0.41
    IsNot
    0.40
    Moscow
    0.39
    Rome
    0.39
    Global
    0.39
    Settings
    0.39
    Activations Density 0.000%

    No Known Activations