© 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. 126147
    Prev
    Next
    INDEX
    Explanations

    items invited to

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

    Social norms, energy dissipation, feelings

    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
    of
    0.44
    ofo
    0.41
    ãi
    0.41
    utani
    0.40
     "@{
    0.40
    for
    0.39
    now
    0.39
    ᴏ
    0.39
    ‍ह
    0.38
    की
    0.38
    POSITIVE LOGITS
     brokerage
    0.47
     הסי
    0.44
    เง
    0.44
     dissent
    0.43
     dissenting
    0.43
     récent
    0.43
    แข่ง
    0.43
    巿
    0.43
     racetrack
    0.43
     viewpoints
    0.42
    Activations Density 0.000%

    No Known Activations