© 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. 27693
    Prev
    Next
    INDEX
    Explanations

    coordinates and locations

    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
     ferric
    0.42
     फर
    0.39
    イス
    0.38
    SERT
    0.37
     hava
    0.37
    degener
    0.37
     ち
    0.37
     nw
    0.36
     marginalised
    0.35
     kitu
    0.35
    POSITIVE LOGITS
    loaders
    0.41
    मंड
    0.39
    场景
    0.39
     View
    0.38
    enarios
    0.38
     Frog
    0.38
     &#
    0.37
     sneaky
    0.37
    abend
    0.37
    霧
    0.37
    Activations Density 0.008%

    No Known Activations