© 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. 240829
    Prev
    Next
    INDEX
    Explanations

    numbers and enumeration

    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
    各位
    0.50
    ↵
    0.49
    popupTheme
    0.49
    protein
    0.48
    mér
    0.47
    ומי
    0.46
    wait
    0.45
    fate
    0.45
    ௐ
    0.45
    neighbor
    0.45
    POSITIVE LOGITS
     Kommentar
    0.51
     Challenges
    0.49
     Buses
    0.46
     THREE
    0.46
     Three
    0.45
     Two
    0.45
     TWO
    0.45
     EUR
    0.44
     ENC
    0.44
     Phill
    0.44
    Activations Density 0.002%

    No Known Activations