© 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. 31-GEMMASCOPE-2-RES-262K
    7. 111505
    Prev
    Next
    INDEX
    Explanations

    child, cultural, historical, intimate relationships

    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_31_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
     reservoirs
    0.52
     saves
    0.51
     découvert
    0.47
    국
    0.46
     across
    0.43
     Antibodies
    0.43
     réserv
    0.43
    ার
    0.43
     cabinets
    0.43
    ურთი
    0.43
    POSITIVE LOGITS
    Device
    0.45
    Usage
    0.45
     вопро
    0.43
    ektedir
    0.43
    än
    0.43
     I
    0.42
    <0x0D>
    0.42
     હે
    0.41
     аспек
    0.41
    Concurrency
    0.41
    Activations Density 0.001%

    No Known Activations