© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 133392
    Prev
    Next
    INDEX
    Explanations

    actions directed or permitted

    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
    الي
    0.46
    ώσει
    0.45
    ្នែក
    0.44
    ্যায়
    0.42
    णाला
    0.41
    നിക്ക്
    0.40
    ยะ
    0.40
    ʸ
    0.40
    ೀರ
    0.40
     руку
    0.40
    POSITIVE LOGITS
     write
    0.41
     encouraged
    0.41
     seeker
    0.40
     to
    0.40
     learned
    0.40
     Seek
    0.40
     seek
    0.39
    Lear
    0.39
     interpreter
    0.38
     inclined
    0.38
    Activations Density 0.014%

    No Known Activations