© 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. 41521
    Prev
    Next
    INDEX
    Explanations

    places and distance

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

    Exploitation, captivity, differences

    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
     ਵੀ
    0.48
     틀
    0.45
     शुगर
    0.45
     চাম
    0.44
     канала
    0.44
    hydes
    0.44
     σο
    0.43
    ジャケット
    0.43
     avocados
    0.43
     VEGFR
    0.43
    POSITIVE LOGITS
    Impress
    0.54
    வசம்
    0.50
     distância
    0.47
     ilgili
    0.47
    ⴳ
    0.46
     referente
    0.46
     farklı
    0.46
     nisam
    0.46
     beeindruck
    0.46
    ър
    0.46
    Activations Density 0.000%

    No Known Activations