© 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. 57081
    Prev
    Next
    INDEX
    Explanations

    drains which

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

    speech and language

    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
    oser
    0.57
    therefore
    0.53
    ental
    0.52
    erva
    0.51
    |,
    0.51
    hence
    0.49
    yo
    0.49
     ترکیب
    0.48
     丨
    0.48
    enta
    0.48
    POSITIVE LOGITS
    л
    0.51
     weihn
    0.50
     Klu
    0.49
    갚
    0.49
     christmas
    0.47
    ла
    0.47
    ланти
    0.47
    வனம்
    0.47
    лас
    0.47
     Vision
    0.46
    Activations Density 0.000%

    No Known Activations