© 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. 153980
    Prev
    Next
    INDEX
    Explanations

    simply this

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

    explaining things to you

    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
    ဝ
    0.51
    ยาว
    0.50
    mazione
    0.49
    kov
    0.49
    unna
    0.48
    愭
    0.48
    ylate
    0.48
    ătoare
    0.47
    嚴重
    0.46
    美国
    0.46
    POSITIVE LOGITS
     Fáb
    0.49
     Munich
    0.46
     Horus
    0.45
     Función
    0.45
     ~,
    0.44
     hierarchical
    0.44
     BJ
    0.44
     (),
    0.44
     ...,
    0.43
     nimble
    0.43
    Activations Density 0.000%

    No Known Activations