© 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. 113478
    Prev
    Next
    INDEX
    Explanations

    mastoiditis

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

    domain enumeration

    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
     v
    0.56
     P
    0.49
     an
    0.48
    ?>
    0.48
    P
    0.47
     g
    0.47
     at
    0.46
     d
    0.46
     all
    0.45
     ad
    0.45
    POSITIVE LOGITS
    berapa
    0.56
    ளுக்கும்
    0.53
     ಅವನ
    0.50
    𝟐
    0.50
    लामा
    0.50
    મા
    0.49
     அனுமதிக்க
    0.49
     кеңселер
    0.49
    кину
    0.49
    ганда
    0.49
    Activations Density 0.003%

    No Known Activations