© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 83123
    Prev
    Next
    INDEX
    Explanations

    cleared its neighborhood

    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
     Yankee
    0.44
     Country
    0.43
    ه
    0.43
     ла
    0.43
     pyramid
    0.41
    ್‌
    0.41
    つき
    0.41
    DOCUMENT
    0.41
     Forward
    0.41
     goldfish
    0.41
    POSITIVE LOGITS
     raí
    0.47
    REDIR
    0.46
    lew
    0.45
    ότητας
    0.45
     qtd
    0.44
     esperienza
    0.44
    ﾚ
    0.44
     jScrollPane
    0.43
    XH
    0.43
    λαν
    0.43
    Activations Density 0.001%

    No Known Activations