© 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. 30689
    Prev
    Next
    INDEX
    Explanations

    key-value pairs

    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
     खैर
    0.40
     indulge
    0.37
    ਈ
    0.35
    аны
    0.34
    autas
    0.34
    ईन
    0.34
    వృద్ధి
    0.33
    voegd
    0.33
     kuri
    0.33
    ஷ்ட
    0.32
    POSITIVE LOGITS
     followed
    0.57
     seguido
    0.51
    followed
    0.50
    @
    0.50
    ].[
    0.49
    [.
    0.49
    @[
    0.44
    _[
    0.43
     diikuti
    0.43
    @(
    0.41
    Activations Density 0.074%

    No Known Activations