© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 21029
    Prev
    Next
    INDEX
    Explanations

    numbers in lists and code

    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
     summar
    0.48
     don
    0.47
     PAR
    0.44
     lem
    0.43
     在
    0.43
     TE
    0.42
     ه
    0.41
     HEN
    0.41
     MEL
    0.41
     în
    0.40
    POSITIVE LOGITS
    зи
    0.55
    ни
    0.50
    リーチ
    0.46
     ইন্ডাস্ট
    0.45
    риа
    0.44
    xym
    0.44
    ﮧ
    0.44
    inį
    0.43
    ة
    0.43
    ња
    0.43
    Activations Density 0.092%

    No Known Activations