© 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. 135635
    Prev
    Next
    INDEX
    Explanations

    requirements

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

    gap widening

    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
     }
    0.52
     besitzt
    0.52
    ierungen
    0.50
     angepasst
    0.48
    {.
    0.45
    ":{"
    0.44
     presenceData
    0.43
     posee
    0.43
     vorhand
    0.43
     }.
    0.43
    POSITIVE LOGITS
    wheels
    0.49
     Wheels
    0.48
    入れる
    0.48
     wheels
    0.47
     কেহ
    0.46
    鬨
    0.46
    ridor
    0.45
    不由
    0.45
     chapel
    0.45
    ვილ
    0.44
    Activations Density 0.001%

    No Known Activations