© 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. 41945
    Prev
    Next
    INDEX
    Explanations

    the, an followed by i- or en-

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

    demanded, pressured, repeatedly

    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
    R
    0.55
    üksek
    0.52
     plán
    0.52
    på
    0.49
    T
    0.48
    L
    0.48
    TUN
    0.48
     köny
    0.47
    E
    0.47
    resto
    0.47
    POSITIVE LOGITS
     inhalation
    0.60
     carcinogenesis
    0.59
     whitish
    0.53
     oneness
    0.50
     exertion
    0.50
     mankind
    0.49
     inasmuch
    0.47
     alleles
    0.47
     erythrocytes
    0.47
     ancients
    0.46
    Activations Density 0.000%

    No Known Activations