© 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. 45803
    Prev
    Next
    INDEX
    Explanations

    ISBN, DOI, URLs

    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
    一批
    0.48
     NSCs
    0.43
    ICAN
    0.43
    ERCIAL
    0.42
    ろしく
    0.42
    如何
    0.41
    处
    0.41
     Racism
    0.41
     एसटी
    0.41
    都已经
    0.41
    POSITIVE LOGITS
     zare
    0.43
    siege
    0.42
     frescoes
    0.42
    ze
    0.41
     კარ
    0.40
    lique
    0.39
     każ
    0.39
    pl
    0.39
    ြ
    0.39
    trz
    0.39
    Activations Density 0.001%

    No Known Activations