© 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. 206424
    Prev
    Next
    INDEX
    Explanations

    infringement or paper

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

    combination or selection

    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
     dystopian
    0.51
    FrameLength
    0.47
     Valentino
    0.46
    धील
    0.45
     Rashford
    0.45
    ﮨ
    0.44
     prestasi
    0.44
     بير
    0.44
     biste
    0.44
     لوبو
    0.44
    POSITIVE LOGITS
     가는
    0.51
    सी
    0.49
     가
    0.49
    도
    0.48
    ne
    0.46
    decay
    0.46
    ong
    0.45
    CA
    0.45
     touching
    0.44
    CARE
    0.43
    Activations Density 0.001%

    No Known Activations