© 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. 40-GEMMASCOPE-2-RES-262K
    7. 22740
    Prev
    Next
    INDEX
    Explanations

    legally owning

    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
     verbatim
    0.44
    直し
    0.41
     triphosphate
    0.40
    ☜
    0.39
    登山
    0.38
    膻
    0.38
    盐
    0.38
    ثل
    0.38
    𝜆
    0.38
    плат
    0.38
    POSITIVE LOGITS
     angling
    0.41
    roke
    0.41
    far
    0.39
     зак
    0.38
    ambu
    0.38
     अँ
    0.38
     sag
    0.37
     reinforce
    0.37
     мероприя
    0.37
    ojen
    0.36
    Activations Density 0.000%

    No Known Activations