© 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. 11000
    Prev
    Next
    INDEX
    Explanations

    section id or headings

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

    segments of information

    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
    6
    0.56
    8
    0.51
     florist
    0.50
     citron
    0.47
     suburban
    0.46
     booth
    0.46
    সির
    0.45
    4
    0.45
    στε
    0.45
     sĩ
    0.45
    POSITIVE LOGITS
     Subsection
    0.51
    talking
    0.46
    때
    0.46
    нету
    0.45
    total
    0.45
    rikt
    0.45
    clear
    0.44
     Abschnitt
    0.44
    a
    0.44
     आईं
    0.43
    Activations Density 0.000%

    No Known Activations