© 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. 99204
    Prev
    Next
    INDEX
    Explanations

    deals and sponsorships

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

    career and personal goals

    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
     bekannt
    0.49
    DBD
    0.48
    𝘿
    0.47
     вероят
    0.46
    Perf
    0.44
    𝘋
    0.44
     ـ
    0.44
     möglicherweise
    0.44
    丽
    0.43
    偣
    0.43
    POSITIVE LOGITS
     bouts
    0.48
     topper
    0.47
     commercials
    0.44
     recurrence
    0.44
     thereto
    0.43
     philanthropic
    0.43
     उठाते
    0.43
     affairs
    0.43
    zość
    0.42
    ಿತು
    0.42
    Activations Density 0.000%

    No Known Activations