© 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. 79822
    Prev
    Next
    INDEX
    Explanations

    not needed

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

    requirements and conditions

    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
    ერს
    0.44
     impossibile
    0.43
     असंभव
    0.40
    ்ச்ச
    0.39
     बुरी
    0.38
     mussten
    0.38
     ہر
    0.38
    㗎
    0.38
    ילו
    0.37
     تمت
    0.37
    POSITIVE LOGITS
    不需要
    0.87
     不需要
    0.73
    ไม่ต้อง
    0.70
    无需
    0.68
    不必
    0.60
     needn
    0.56
    不用
    0.52
    只需要
    0.52
     behov
    0.50
    無需
    0.50
    Activations Density 0.146%

    No Known Activations