© 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. 234863
    Prev
    Next
    INDEX
    Explanations

    authors whom

    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
     துரு
    0.47
     неот
    0.46
     அதிகார
    0.45
     Надо
    0.44
    >→</
    0.44
     المصطلح
    0.44
    implicitly
    0.44
     adduced
    0.44
     сро
    0.43
     precisam
    0.43
    POSITIVE LOGITS
    S
    0.55
    M
    0.53
    C
    0.52
    ber
    0.51
    周边
    0.50
    D
    0.50
    E
    0.50
    データ
    0.49
    ब
    0.49
    O
    0.48
    Activations Density 0.002%

    No Known Activations