© 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. 3399
    Prev
    Next
    INDEX
    Explanations

    specific concepts and phrases

    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
     kertas
    0.61
    ଵ
    0.58
     siis
    0.50
     braucht
    0.50
    🗼
    0.49
    秸
    0.48
     bekommt
    0.48
     átomos
    0.48
     да
    0.47
     könnt
    0.47
    POSITIVE LOGITS
    DC
    0.52
    En
    0.51
    It
    0.51
    System
    0.51
     Vance
    0.49
    7
    0.48
    International
    0.47
    Modifier
    0.46
    Tracks
    0.45
    Op
    0.44
    Activations Density 0.001%

    No Known Activations