© 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. 132322
    Prev
    Next
    INDEX
    Explanations

    code structures and parameters

    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
    ಷ
    0.40
    नियों
    0.39
     Informe
    0.39
     hypersur
    0.38
     cirrh
    0.38
    ورہ
    0.38
    այի
    0.37
    ⚉
    0.37
    गर
    0.37
    साय
    0.37
    POSITIVE LOGITS
     கீ
    0.42
     कोल
    0.38
     sell
    0.37
     widest
    0.36
    鮮
    0.36
     pine
    0.36
    ೋಪ
    0.35
     Half
    0.35
     ਉ
    0.34
     manufacture
    0.34
    Activations Density 0.010%

    No Known Activations