© 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. 131617
    Prev
    Next
    INDEX
    Explanations

    building or crafting

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

    Beyond the Hype

    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
    悴
    0.50
     managable
    0.49
     adlı
    0.46
    的操作
    0.45
     yandan
    0.45
    りの
    0.44
    由来
    0.44
     gás
    0.43
    歪
    0.43
     Gasoline
    0.43
    POSITIVE LOGITS
    uk
    0.58
    amps
    0.56
    MF
    0.53
    enc
    0.52
    MPs
    0.52
    fair
    0.52
    midd
    0.51
    nos
    0.51
    dat
    0.50
    oz
    0.50
    Activations Density 0.000%

    No Known Activations