© 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. 156701
    Prev
    Next
    INDEX
    Explanations

    accuse conservatives, balance, capitalize on, generous contributors

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

    birds

    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
     belangrijk
    0.50
    되고
    0.46
     penting
    0.46
     Meghna
    0.46
     important
    0.45
    6
    0.45
     wszyscy
    0.44
    ew
    0.44
     wichtig
    0.44
     atractivo
    0.44
    POSITIVE LOGITS
    芜
    0.47
    wam
    0.44
    otá
    0.42
    dil
    0.41
    
    0.41
    辈
    0.41
    記憶
    0.41
    塭
    0.40
    munder
    0.40
     Canoe
    0.40
    Activations Density 0.000%

    No Known Activations