© 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. 23506
    Prev
    Next
    INDEX
    Explanations

    special

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

    specialized or specific

    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
    寐
    0.40
     copyspace
    0.40
    虎
    0.40
     অপর
    0.37
    買い物
    0.37
     ondas
    0.36
    𝗆
    0.36
    骋
    0.36
    FileList
    0.36
    جمالي
    0.35
    POSITIVE LOGITS
     special
    1.75
     специа
    1.70
     спеціа
    1.70
     specialized
    1.66
     speciale
    1.63
    special
    1.59
    特殊
    1.59
     specially
    1.57
     специальные
    1.56
     spezielle
    1.55
    Activations Density 0.274%

    No Known Activations