© 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. 31-GEMMASCOPE-2-RES-65K
    4. 27740
    Prev
    Next
    INDEX
    Explanations

    landslide, wave, cliff, avalanche

    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_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
     coordinates
    0.46
     परिचाल
    0.44
     Melbourne
    0.42
     queim
    0.42
    膀
    0.42
     cooling
    0.42
     координаты
    0.42
     metallurgy
    0.41
     subtropical
    0.41
    actus
    0.41
    POSITIVE LOGITS
     landslide
    0.73
     landslides
    0.64
     avalanche
    0.48
     boulder
    0.48
    Flood
    0.48
     cliff
    0.46
    flood
    0.45
     Flood
    0.45
    ชน
    0.44
    陡
    0.44
    Activations Density 0.048%

    No Known Activations