© 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. 210817
    Prev
    Next
    INDEX
    Explanations

    partial words and phrases

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

    who is for

    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
     esso
    0.45
     tomada
    0.44
    会将
    0.40
     bijzonder
    0.40
    箕
    0.39
     miejscowości
    0.38
    我自己
    0.38
     fijn
    0.38
    给予
    0.38
     hét
    0.38
    POSITIVE LOGITS
    O
    0.51
    P
    0.48
     அவற்றை
    0.47
    a
    0.47
     ATL
    0.47
    Trans
    0.46
    switching
    0.45
    osph
    0.45
    absolute
    0.45
    re
    0.45
    Activations Density 0.001%

    No Known Activations