© 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. 221631
    Prev
    Next
    INDEX
    Explanations

    purchase agreement or atheist rituals

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

    training data limitations

    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
    崛起
    0.48
     비슷
    0.47
    攝
    0.46
     독일
    0.46
    瑠
    0.46
    餌
    0.45
    德國
    0.45
     తనకు
    0.44
    inducing
    0.44
    を使
    0.43
    POSITIVE LOGITS
     have
    0.52
     Lincoln
    0.48
    Lincoln
    0.47
     in
    0.46
    CA
    0.46
     $
    0.46
     $+
    0.46
    AAA
    0.45
     Nielsen
    0.44
    Jets
    0.44
    Activations Density 0.000%

    No Known Activations