© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 1274
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives

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

    -based descriptors

    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_53_width_65k_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
     는
    0.34
     JavaBeans
    0.34
     extrait
    0.31
     بیټ
    0.31
    ≥</
    0.31
     combien
    0.31
     QuantityOnHand
    0.31
     logarithms
    0.30
     অবশ্যই
    0.30
     BLUENRG
    0.30
    POSITIVE LOGITS
    based
    0.64
    sized
    0.63
    related
    0.59
    footed
    0.58
    oriented
    0.57
    minded
    0.57
    level
    0.55
    ‐
    0.55
    backed
    0.54
    grained
    0.54
    Activations Density 0.588%

    No Known Activations