© 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. 40-GEMMASCOPE-2-RES-262K
    7. 1723
    Prev
    Next
    INDEX
    Explanations

    variational inference, cards, pulse

    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_40_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
    所属
    0.43
     ແລະ
    0.41
    ிருப்ப
    0.40
    espèces
    0.40
    士
    0.40
    種
    0.40
    来て
    0.39
    გუფი
    0.39
    ğaz
    0.39
     Ila
    0.39
    POSITIVE LOGITS
    iegel
    0.45
     browser
    0.44
     Citizenship
    0.42
    el
    0.42
     فرمایا
    0.41
     انته
    0.41
    at
    0.41
     Fü
    0.41
    **:
    0.40
     minim
    0.40
    Activations Density 0.000%

    No Known Activations