© 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. 224356
    Prev
    Next
    INDEX
    Explanations

    descriptive words and identifiers

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

    support, focus, ability, movement

    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
    ين
    0.56
     famosos
    0.47
    تي
    0.46
    تى
    0.45
    تش
    0.45
    魁
    0.44
     schermo
    0.43
    gll
    0.43
    ᡳ
    0.43
    েল
    0.43
    POSITIVE LOGITS
     เพื่อน
    0.47
     muc
    0.44
     รัก
    0.44
     근
    0.44
     뭔가
    0.43
     inducible
    0.43
     muk
    0.43
     ร่วม
    0.43
     เย
    0.42
     व्यवसाय
    0.42
    Activations Density 0.002%

    No Known Activations