© 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. 64017
    Prev
    Next
    INDEX
    Explanations

    do your own thing

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

    Festival, December, party

    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
    囪
    0.50
     நாட்களில்
    0.49
     রাস্ত
    0.48
     நாட்க
    0.48
     hạn
    0.48
     اقسام
    0.47
    氈
    0.47
    を防
    0.46
    大多數
    0.45
    وتر
    0.45
    POSITIVE LOGITS
     yum
    0.48
    å
    0.45
     शख्स
    0.45
    Ah
    0.44
    Mk
    0.44
    ATHER
    0.44
    Ex
    0.43
    u
    0.43
    Speaker
    0.41
    あ
    0.41
    Activations Density 0.001%

    No Known Activations