© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 78949
    Prev
    Next
    INDEX
    Explanations

    listing items after separators

    np_acts-logits-general · gemini-2.5-flash-lite

    setting context and meaning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    т
    0.54
    ж
    0.54
    1
    0.53
    4
    0.53
    Ar
    0.51
    2
    0.50
    jah
    0.48
    ã
    0.47
    zo
    0.46
    zh
    0.46
    POSITIVE LOGITS
     fråga
    0.49
     differentiator
    0.49
    ట్టిన
    0.48
     curtail
    0.47
    僞
    0.47
     creditor
    0.45
    蟶
    0.45
    謖
    0.45
     বাড়ানোর
    0.44
    ডাক্ট
    0.44
    Activations Density 0.000%

    No Known Activations