© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 100569
    Prev
    Next
    INDEX
    Explanations

    legal and business processes

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

    included notes or explanations

    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
     Soh
    0.51
     Zoho
    0.48
     Nunes
    0.48
     ANGE
    0.47
    (-
    0.46
     Yangzhou
    0.45
     Bhajan
    0.44
    ዷ
    0.44
     KM
    0.44
     Bec
    0.44
    POSITIVE LOGITS
     گراف
    0.54
    RAFT
    0.53
    苏联
    0.48
     فیلم
    0.48
     تجهیز
    0.48
     څرنګوالی
    0.47
    شهر
    0.47
    setCharacter
    0.46
    وق
    0.46
     گروه
    0.45
    Activations Density 0.001%

    No Known Activations