© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 109872
    Prev
    Next
    INDEX
    Explanations

    binary outcome, PPC, work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ફો
    0.42
     Villanueva
    0.41
    的美
    0.40
    ꯃ
    0.40
    நாயக
    0.39
    ్రియ
    0.39
    buch
    0.38
     visão
    0.38
     అధ్యక్ష
    0.38
    埜
    0.38
    POSITIVE LOGITS
     six
    0.42
     vrij
    0.41
     peaks
    0.41
    дается
    0.41
     pull
    0.40
     +
    0.40
     ups
    0.39
     try
    0.39
     vouloir
    0.39
     posibilidades
    0.39
    Activations Density 0.001%

    No Known Activations