© 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. 154297
    Prev
    Next
    INDEX
    Explanations

    comedy, SERIES

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

    list of supplies

    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
    ترام
    0.50
    یک
    0.50
     ближай
    0.47
    ])):
    0.46
     nearby
    0.43
    徒歩
    0.42
     نزدیک
    0.41
     زیبا
    0.41
    )]:
    0.41
    0
    0.41
    POSITIVE LOGITS
    GoObject
    0.52
     abuso
    0.52
     aumento
    0.51
     oi
    0.51
    бе
    0.50
    нос
    0.50
    माजिक
    0.49
    ப்பன்
    0.48
    τε
    0.48
    ем
    0.47
    Activations Density 0.000%

    No Known Activations