© 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. 142303
    Prev
    Next
    INDEX
    Explanations

    conditions for

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

    while flexibility

    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
    brochen
    0.46
     Sald
    0.46
    郸
    0.45
    ían
    0.44
     nächsten
    0.44
     断
    0.44
     Martín
    0.44
     Jangan
    0.43
    declaration
    0.43
     अगली
    0.43
    POSITIVE LOGITS
     celebrations
    0.56
     celebrating
    0.49
    ckiego
    0.47
    ों
    0.47
     executar
    0.47
     retirees
    0.46
    Celebrating
    0.44
     Creators
    0.44
    υ
    0.44
    警
    0.44
    Activations Density 0.000%

    No Known Activations