© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 134316
    Prev
    Next
    INDEX
    Explanations

    dentists and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    зия
    0.41
     ಅಮ
    0.40
    핑
    0.40
    HQ
    0.39
    Homes
    0.39
    に変更
    0.39
    Corp
    0.38
    เสนอ
    0.38
    궬
    0.38
    fting
    0.38
    POSITIVE LOGITS
     brownish
    0.43
     punte
    0.41
     dentists
    0.40
     kneeling
    0.40
     dentist
    0.39
     characterised
    0.39
     khas
    0.39
     zeich
    0.39
     mitral
    0.39
    endant
    0.38
    Activations Density 0.000%

    No Known Activations