© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3011
    Prev
    Next
    INDEX
    Explanations

    my side, your side

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

    your side or server-side

    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
     ullam
    0.36
    igsaw
    0.35
    枃
    0.34
    uffix
    0.33
    INTRESOURCE
    0.33
    ificat
    0.33
    ritical
    0.32
    ற்று
    0.32
     lont
    0.31
     शकत
    0.31
    POSITIVE LOGITS
     side
    4.88
     Side
    4.50
    Side
    4.41
    side
    4.38
     SIDE
    4.19
    側
    4.06
    侧
    4.03
    SIDE
    3.97
     sides
    3.92
     сторона
    3.72
    Activations Density 0.398%

    No Known Activations