© 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. 16660
    Prev
    Next
    INDEX
    Explanations

    wedding rings

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

    professional, brethren, visible

    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
    秏
    0.46
    磊
    0.43
    啰
    0.43
     OHIO
    0.42
    𝐫
    0.42
    𝒓
    0.42
    🏹
    0.42
     partie
    0.41
    icolo
    0.41
    𝒊
    0.41
    POSITIVE LOGITS
     adjusts
    0.49
     analyzes
    0.47
    водится
    0.46
     powders
    0.45
     conducts
    0.45
     adjustments
    0.44
     chickens
    0.44
    azan
    0.42
     bears
    0.41
     mobilizing
    0.41
    Activations Density 0.007%

    No Known Activations