© 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. 46326
    Prev
    Next
    INDEX
    Explanations

    weeks and months

    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
     wreak
    0.47
     compromising
    0.46
    с
    0.46
     exasper
    0.44
     frantically
    0.44
     निजी
    0.44
     defect
    0.44
     privy
    0.44
     privately
    0.43
     곧
    0.43
    POSITIVE LOGITS
     isotropic
    0.45
     introns
    0.45
     isomerization
    0.45
    ؤال
    0.44
     Awakening
    0.43
     anthracene
    0.42
     organik
    0.42
     APIDC
    0.41
     isomeric
    0.41
     Organic
    0.40
    Activations Density 0.004%

    No Known Activations