© 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. 199733
    Prev
    Next
    INDEX
    Explanations

    demonstrative determiners and words

    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
     dục
    0.47
     бк
    0.46
     যের
    0.45
    볐
    0.44
     andRow
    0.44
     sẵn
    0.43
     निम्
    0.42
    дын
    0.42
     والصلاه
    0.42
    lookandfeel
    0.42
    POSITIVE LOGITS
    d
    0.59
    kos
    0.56
    L
    0.53
    ys
    0.51
    con
    0.50
    W
    0.50
    T
    0.49
    is
    0.49
    cal
    0.49
    B
    0.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.