© 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. 53-GEMMASCOPE-2-RES-65K
    7. 8047
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives

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

    qualifier then object

    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
     which
    0.55
    ;
    0.54
     that
    0.52
        
    0.52
     including
    0.50
     the
    0.50
    :
    0.49
     with
    0.49
     a
    0.47
     being
    0.46
    POSITIVE LOGITS
     glycos
    0.57
     mRNAs
    0.50
     introns
    0.50
     hadrons
    0.50
     erythrocytes
    0.49
     snowfall
    0.49
     prépuce
    0.48
     neutrophils
    0.48
     mandibular
    0.47
     ulcers
    0.45
    Activations Density 0.580%

    No Known Activations