© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 62435
    Prev
    Next
    INDEX
    Explanations

    deformities and medical 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_31_width_65k_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
    फार
    0.42
     Huyền
    0.42
     कांटे
    0.41
    飚
    0.39
    幽
    0.39
    cleaned
    0.38
    extracted
    0.38
     pleasurable
    0.38
    脂
    0.38
     удовлетво
    0.38
    POSITIVE LOGITS
     Pool
    0.44
     Win
    0.43
     Chain
    0.41
     Marshall
    0.40
    釟
    0.40
     win
    0.39
     mas
    0.39
     leg
    0.39
     nghi
    0.39
     deform
    0.39
    Activations Density 0.020%

    No Known Activations