© 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. 54853
    Prev
    Next
    INDEX
    Explanations

    It's definitions

    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
     +
    0.55
     function
    0.50
     functions
    0.50
    (
    0.50
    +
    0.50
     features
    0.49
     it
    0.48
     you
    0.48
     is
    0.47
     integrates
    0.46
    POSITIVE LOGITS
    禳
    0.43
    徫
    0.43
     enfermos
    0.42
    asını
    0.41
    antiti
    0.40
    駑
    0.39
    avgsalary
    0.39
     સારી
    0.38
    쵝
    0.38
     kuda
    0.38
    Activations Density 0.062%

    No Known Activations