© 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. 18697
    Prev
    Next
    INDEX
    Explanations

    dental health and dental procedures

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

    dental procedures and oral health

    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
    咥
    0.51
    জনক
    0.46
     prostagland
    0.45
     कोले
    0.45
    顎
    0.44
     سنت
    0.44
    颚
    0.43
    痤
    0.43
     TNF
    0.42
     Throat
    0.42
    POSITIVE LOGITS
     varnish
    0.43
     injection
    0.40
    Injection
    0.40
    Painting
    0.40
     fluorescence
    0.39
     Injection
    0.38
    Sugar
    0.38
    sugar
    0.38
    漓
    0.38
    varn
    0.38
    Activations Density 0.099%

    No Known Activations