© 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. 40559
    Prev
    Next
    INDEX
    Explanations

    specific entities and names

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

    operations, feedback, and dispatch

    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
     άλ
    0.55
     फेब्रुवारी
    0.48
     gezogen
    0.46
     ειδ
    0.46
     gelegt
    0.46
    𝐠
    0.45
    ங்கல்
    0.45
    especially
    0.45
    𝘭
    0.44
    trä
    0.43
    POSITIVE LOGITS
    стива
    0.52
    시면
    0.46
    ного
    0.43
    시켜
    0.42
     Cafe
    0.42
    리티
    0.41
    akuza
    0.41
    df
    0.40
     Oyun
    0.40
    ioned
    0.40
    Activations Density 0.000%

    No Known Activations