© 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. 128508
    Prev
    Next
    INDEX
    Explanations

    for accurate reproduction

    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
    1
    0.57
    kar
    0.44
    maar
    0.44
    pra
    0.44
    p
    0.44
    9
    0.43
     August
    0.43
    3
    0.43
     bulan
    0.42
     s
    0.42
    POSITIVE LOGITS
     commens
    0.51
    точно
    0.47
     Instrumented
    0.47
    ARDS
    0.44
    መሳ
    0.44
     shorthand
    0.44
    బ్బ
    0.43
     réduction
    0.43
     использу
    0.43
    сист
    0.43
    Activations Density 0.014%

    No Known Activations