© 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. 21212
    Prev
    Next
    INDEX
    Explanations

    examples followed by code or question

    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
    𝘔
    0.48
    𝟮
    0.45
    各種
    0.45
    ágoras
    0.45
    𝘁
    0.43
    𝘱
    0.42
    ুল
    0.41
    𝘖
    0.41
    Plug
    0.41
    ^{*}}\
    0.41
    POSITIVE LOGITS
     When
    0.61
     Якщо
    0.55
     There
    0.55
     Where
    0.53
     But
    0.50
     Telephone
    0.49
     Если
    0.48
     Only
    0.48
     Maybe
    0.48
     Alternatively
    0.47
    Activations Density 0.005%

    No Known Activations