© 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. 41-GEMMASCOPE-2-RES-262K
    7. 198052
    Prev
    Next
    INDEX
    Explanations

    effective depth, technical fit, technique

    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_all/layer_41_width_262k_l0_big
    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
     braid
    0.43
     salad
    0.42
    وە
    0.38
    痩
    0.38
    schaft
    0.37
     Salad
    0.36
    錯
    0.36
    ビル
    0.36
    भगवान
    0.35
    یان
    0.35
    POSITIVE LOGITS
     depois
    0.44
     indicadores
    0.42
    Heights
    0.41
     tek
    0.41
    katapos
    0.41
    Computed
    0.40
    visao
    0.40
     Geometric
    0.39
     discord
    0.39
     tantos
    0.39
    Activations Density 0.000%

    No Known Activations