© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 134041
    Prev
    Next
    INDEX
    Explanations

    contact us, fulfill request

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

    Zen Buddhist concepts

    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_31_width_262k_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
    y
    0.52
     Deport
    0.47
    キャリア
    0.47
     $)$
    0.46
     સુ
    0.45
     Bismillahirrah
    0.45
     Cappadocia
    0.45
    ا
    0.45
    o
    0.45
    ইয়া
    0.44
    POSITIVE LOGITS
    unden
    0.55
     construe
    0.49
     వారికి
    0.47
    ;
    0.47
     theology
    0.45
     grate
    0.45
     frighten
    0.44
    ᱘
    0.43
    чает
    0.43
     fright
    0.42
    Activations Density 0.000%

    No Known Activations