© 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. 194377
    Prev
    Next
    INDEX
    Explanations

    cubes

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

    place to

    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
     เมือง
    0.52
    วย
    0.51
     บ้าน
    0.49
    〟
    0.49
     atraves
    0.49
     página
    0.48
     เรือ
    0.48
    DeleteDialogOpen
    0.47
     നട
    0.47
     garner
    0.47
    POSITIVE LOGITS
     fasten
    0.50
     fasteners
    0.49
    %%
    0.43
     painkillers
    0.43
    mede
    0.42
    taj
    0.42
     fastening
    0.41
     floss
    0.41
    isture
    0.41
     specials
    0.41
    Activations Density 0.000%

    No Known Activations