© 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. 3479
    Prev
    Next
    INDEX
    Explanations

    ed by

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

    alternative classifications or debunking claims

    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
    ᴥ
    0.43
    Aust
    0.39
     அன்பு
    0.38
     lieben
    0.38
    戀
    0.38
     Fits
    0.38
    袖
    0.38
    çons
    0.37
    觅
    0.37
    مي
    0.37
    POSITIVE LOGITS
    gele
    0.40
    blowing
    0.38
    сль
    0.37
    jogo
    0.36
    +(-
    0.35
     фаразы
    0.35
    stven
    0.34
     conco
    0.34
    horns
    0.34
     thoroughly
    0.33
    Activations Density 0.000%

    No Known Activations