© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92724
    Prev
    Next
    INDEX
    Explanations

    reducing entropy, caveats

    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
     recuperar
    0.42
     Abandon
    0.41
    spot
    0.41
     alcanzar
    0.39
     Scenes
    0.38
     Vav
    0.38
    >(&
    0.38
     enca
    0.37
     Ard
    0.37
     microbiota
    0.37
    POSITIVE LOGITS
    iegel
    0.48
    ėmis
    0.48
    ної
    0.47
    chränk
    0.46
     müş
    0.45
    íř
    0.45
    iggers
    0.45
    WON
    0.45
    ﺔ
    0.45
    车型
    0.44
    Activations Density 0.014%

    No Known Activations