© 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-16K
    7. 13740
    Prev
    Next
    INDEX
    Explanations

    spaceships or physical space

    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_16k_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
    S
    0.56
    st
    0.54
    P
    0.53
    ir
    0.52
    con
    0.52
    '
    0.49
    यॉर्क
    0.49
     a
    0.48
    up
    0.48
    vény
    0.48
    POSITIVE LOGITS
     space
    1.38
     Space
    1.35
     ruimte
    1.19
     spaces
    1.18
     공간
    1.18
     espacio
    1.17
     SPACE
    1.14
     spazio
    1.13
    スペース
    1.13
    space
    1.13
    Activations Density 0.225%

    No Known Activations