© 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. 55191
    Prev
    Next
    INDEX
    Explanations

    that followed by verb or pronoun

    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
     humanidad
    0.47
     rad
    0.45
     lookout
    0.45
     pewter
    0.45
    ↵↵
    0.44
     excused
    0.44
    それを
    0.43
     préférable
    0.43
     hogy
    0.43
    ों
    0.43
    POSITIVE LOGITS
    is
    0.52
     enables
    0.52
    makes
    0.51
     underlies
    0.51
     was
    0.49
    й
    0.48
    ched
    0.47
     makes
    0.47
     позволяет
    0.47
     comes
    0.46
    Activations Density 0.001%

    No Known Activations