© 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. 22338
    Prev
    Next
    INDEX
    Explanations

    aqua, pink, worker, ocean blue

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

    omniture user behavior data

    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
     groundwork
    0.52
    }}^{
    0.49
     अर्थात्
    0.48
     Comedy
    0.48
    acious
    0.47
     tournaments
    0.46
     Participants
    0.46
    వరకు
    0.46
    ogram
    0.46
    naments
    0.45
    POSITIVE LOGITS
     estamp
    0.54
     discíp
    0.46
     suốt
    0.46
     возможности
    0.45
     fii
    0.45
     reconnaît
    0.44
    ህ
    0.43
     сотруд
    0.43
     surfer
    0.43
    ጵ
    0.43
    Activations Density 0.002%

    No Known Activations