© 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. 46367
    Prev
    Next
    INDEX
    Explanations

    combined with trust

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

    maps and territories

    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
    sembly
    0.47
     SYM
    0.47
    s
    0.45
    iderm
    0.44
    保护
    0.42
    itled
    0.41
    ंसर
    0.41
    如此
    0.41
     ఇలా
    0.41
     រ
    0.41
    POSITIVE LOGITS
     Namibia
    0.52
     Vanuatu
    0.51
     Canarias
    0.50
    𝓽
    0.50
     Andorra
    0.49
     कार्ट
    0.48
     situatie
    0.47
     Faroe
    0.47
     γά
    0.47
     cambiamenti
    0.47
    Activations Density 0.000%

    No Known Activations