© 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. 122550
    Prev
    Next
    INDEX
    Explanations

    dealing with single source

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

    questions and choices about you

    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
     くれ
    0.40
    ப்படுத்தும்
    0.40
    ᐳ
    0.40
    pretty
    0.39
    欧盟
    0.39
     পাকিস্তানী
    0.39
    ξύ
    0.39
    梸
    0.38
    虽然
    0.38
    ᐸ
    0.38
    POSITIVE LOGITS
     Ch
    0.46
    itya
    0.45
     Franz
    0.44
     inability
    0.43
     Gonzalo
    0.43
     Fragmentation
    0.43
     chronological
    0.43
     emergencies
    0.42
     fragmentation
    0.42
     graveyard
    0.42
    Activations Density 0.001%

    No Known Activations