© 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. 27908
    Prev
    Next
    INDEX
    Explanations

    phrase endings or connectors

    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
     platelet
    0.42
     alamy
    0.42
    ᓚ
    0.42
    erald
    0.41
     ಫ
    0.40
     गढ़
    0.39
    ئو
    0.39
     clearer
    0.39
     القدر
    0.39
    ਗਾ
    0.39
    POSITIVE LOGITS
    Finish
    0.38
    etis
    0.36
     fucked
    0.35
    Ys
    0.35
     mixtures
    0.35
    sense
    0.35
     screwed
    0.34
    ҫ
    0.34
    separ
    0.33
    orde
    0.33
    Activations Density 0.049%

    No Known Activations