© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 235
    Prev
    Next
    INDEX
    Explanations

    going ahead or back

    np_acts-logits-general · gemini-2.5-flash-lite

    go beyond

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Secara
    0.36
    ENSATION
    0.27
    =(-
    0.26
     //-
    0.26
    themem
    0.26
     keter
    0.26
    ايات
    0.26
    튿
    0.26
    )//
    0.25
    제가
    0.25
    POSITIVE LOGITS
     overboard
    0.74
     ahead
    0.66
     crazy
    0.60
    ofed
    0.60
     astray
    0.59
     nuts
    0.56
     bankrupt
    0.56
     back
    0.55
     into
    0.55
     unnoticed
    0.55
    Activations Density 0.200%

    No Known Activations