© 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. 62342
    Prev
    Next
    INDEX
    Explanations

    simulate actual

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

    names, specific conditions, egg yolks

    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
     অথবা
    0.57
     अथवा
    0.57
     또는
    0.55
     or
    0.53
    หรือ
    0.52
    或者
    0.52
    もしくは
    0.51
    或
    0.51
     alebo
    0.50
     혹은
    0.49
    POSITIVE LOGITS
     haci
    0.53
     vitth
    0.51
    స్టు
    0.51
    серва
    0.50
    спеди
    0.47
     экспеди
    0.46
     nanti
    0.46
     kilomet
    0.46
     VIR
    0.45
    Ꮦ
    0.45
    Activations Density 0.000%

    No Known Activations