© 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-3-270M-IT
    3. 12-GEMMASCOPE-2-RES-65K
    4. 310
    Prev
    Next
    INDEX
    Explanations

    from this, conditions in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
    Ⲣ
    0.83
     Ramb
    0.77
     неуда
    0.75
     nags
    0.74
     Tuy
    0.74
    แซ
    0.73
    Ꮲ
    0.73
     sửa
    0.71
    𝒃
    0.71
     يص
    0.70
    POSITIVE LOGITS
    Background
    1.40
    rones
    1.35
    Areas
    1.35
    Drone
    1.35
    "
    1.32
    ↵↵
    1.31
    concept
    1.31
    [
    1.30
    System
    1.30
    owed
    1.29
    Activations Density 0.619%

    No Known Activations