© 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. 11335
    Prev
    Next
    INDEX
    Explanations

    time, place, object, qualification, usage

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

    information and contexts

    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
     sogenannten
    0.37
     kleinen
    0.35
     kleine
    0.34
    ش
    0.34
     nuovamente
    0.33
    യുടെ
    0.33
     deuxième
    0.33
     nouveaux
    0.33
     persönlichen
    0.32
     zusätzlichen
    0.32
    POSITIVE LOGITS
    均为
    0.31
    
    0.30
     ζωή
    0.30
     包括
    0.30
    一般来说
    0.30
    蛲
    0.29
    INGS
    0.28
     勺
    0.28
    全局
    0.27
    ทั้งหมด
    0.27
    Activations Density 0.035%

    No Known Activations