© 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. 31-GEMMASCOPE-2-RES-262K
    7. 57284
    Prev
    Next
    INDEX
    Explanations

    tooth decay and cavities

    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_31_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
     $((
    0.46
     forfait
    0.42
    铱
    0.41
     미술
    0.40
     tanti
    0.40
     pake
    0.40
    χ
    0.40
     אר
    0.39
    ಾರ್
    0.38
     વર્ષ
    0.38
    POSITIVE LOGITS
     consolation
    0.43
     தீங்கு
    0.41
    ats
    0.41
     lightning
    0.41
    at
    0.41
    ogas
    0.40
    imals
    0.40
     zombie
    0.39
    काळ
    0.39
    condensation
    0.39
    Activations Density 0.007%

    No Known Activations