© 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. 73445
    Prev
    Next
    INDEX
    Explanations

    conjunctions for contrast

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

    however

    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
    ן
    0.98
    と
    0.77
    や
    0.77
    ری
    0.75
    rho
    0.70
    க்கு
    0.70
    𝟯
    0.69
    नं
    0.69
    のは
    0.68
    ویت
    0.68
    POSITIVE LOGITS
    c
    1.02
    k
    1.02
    LE
    0.90
    K
    0.89
    B
    0.88
     azonban
    0.87
    V
    0.87
    d
    0.85
    r
    0.83
    ik
    0.82
    Activations Density 0.034%

    No Known Activations