© 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. 169933
    Prev
    Next
    INDEX
    Explanations

    looking for or looking to

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

    looking for or identifying

    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
     sổ
    0.54
     فونبیټ
    0.53
     laquelle
    0.52
     quoique
    0.51
     tampa
    0.50
     ܡ
    0.50
     comprensión
    0.49
     délégation
    0.47
     mua
    0.47
    㴬
    0.47
    POSITIVE LOGITS
    ’
    0.51
    ل
    0.45
     Target
    0.45
    B
    0.44
    лер
    0.44
    Target
    0.43
    Result
    0.42
    n
    0.42
    x
    0.42
     Goodrich
    0.40
    Activations Density 0.001%

    No Known Activations