© 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. 68553
    Prev
    Next
    INDEX
    Explanations

    causes of

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

    foreign language and technical terms

    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
    is
    0.51
    ui
    0.45
    Fiction
    0.44
    yn
    0.42
    জ্জ
    0.41
    gnię
    0.41
    泬
    0.41
    нең
    0.41
    ి
    0.41
    रोग
    0.41
    POSITIVE LOGITS
     dó
    0.48
     privy
    0.48
     décl
    0.46
     geändert
    0.46
     relegated
    0.45
     to
    0.44
     devolved
    0.44
     equil
    0.44
     níveis
    0.44
     INTO
    0.44
    Activations Density 0.000%

    No Known Activations