© 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. 3127
    Prev
    Next
    INDEX
    Explanations

    celestial phenomena and astronomy

    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
     праців
    0.54
    ⸩
    0.53
    匮
    0.52
    팻
    0.52
     pcMove
    0.52
     уйнау
    0.51
     पाटील
    0.51
    谨慎
    0.51
    资本
    0.50
    荤
    0.50
    POSITIVE LOGITS
     eclipse
    0.94
     eclips
    0.83
     celestial
    0.80
     astronomers
    0.72
     phenomena
    0.71
     solar
    0.70
     phenomenon
    0.70
     astronomy
    0.70
    NASA
    0.68
     telescopes
    0.68
    Activations Density 0.078%

    No Known Activations