© 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. 240512
    Prev
    Next
    INDEX
    Explanations

    Kendall Park

    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
     have
    0.45
    SourceIP
    0.44
     showbiz
    0.43
    ারে
    0.42
     fils
    0.42
     leurs
    0.42
     semangat
    0.42
    惀
    0.42
    шымта
    0.42
     পারেনি
    0.41
    POSITIVE LOGITS
    вин
    0.54
    trivial
    0.53
     อ่า
    0.49
    introdu
    0.48
     கூறு
    0.47
     sporadic
    0.46
     consta
    0.46
    robust
    0.46
     avaliar
    0.46
    конструк
    0.45
    Activations Density 0.000%

    No Known Activations