© 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. 199657
    Prev
    Next
    INDEX
    Explanations

    periodontal disease

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

    running things on limited hardware

    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
    bec
    0.49
    埗
    0.46
    契約
    0.45
    وا
    0.44
    nica
    0.43
    ны
    0.43
    лови
    0.42
    UserDetails
    0.41
    ட்ட
    0.41
    燮
    0.41
    POSITIVE LOGITS
     dihydro
    0.54
    EMENTS
    0.49
     excitation
    0.49
     proinflammatory
    0.49
     amusement
    0.48
     prohibitive
    0.48
     propagation
    0.48
     sinusoidal
    0.48
     birefringence
    0.47
     luminosity
    0.47
    Activations Density 0.000%

    No Known Activations