© 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. 41391
    Prev
    Next
    INDEX
    Explanations

    richness and abundance

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

    rich in

    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
    一
    0.61
    ب
    0.60
    方式
    0.58
    ą
    0.56
    an
    0.54
    nto
    0.54
    一座
    0.53
    d
    0.53
    高速
    0.53
     catheters
    0.52
    POSITIVE LOGITS
     richer
    1.36
     richness
    1.23
     rich
    1.20
     enrichment
    1.09
     riche
    1.09
     enriching
    1.07
     Rich
    1.06
    rich
    1.05
     enrich
    1.02
    丰富
    1.02
    Activations Density 0.048%

    No Known Activations