© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 163862
    Prev
    Next
    INDEX
    Explanations

    blue print, carbon dioxide, IRC channel

    np_acts-logits-general · gemini-2.5-flash-lite

    potential keywords or phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     streamed
    0.46
    ρχ
    0.42
    あ
    0.40
    THAT
    0.39
    setPosition
    0.39
    overleftarrow
    0.39
    executionContext
    0.39
    霊
    0.39
     virtue
    0.38
     clearContext
    0.38
    POSITIVE LOGITS
    winkel
    0.51
     antics
    0.50
     کئی
    0.47
     एमएस
    0.47
    en
    0.46
     പദ്ധതി
    0.46
     범위
    0.46
     Amenities
    0.46
    危害
    0.45
     стаўкі
    0.45
    Activations Density 0.000%

    No Known Activations