© 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. 47400
    Prev
    Next
    INDEX
    Explanations

    problem descriptions and solutions

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

    single mom since starting point base requests

    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
     ƒ
    0.49
    ))>
    0.46
     nutric
    0.45
    ρκ
    0.44
     ndani
    0.44
     maig
    0.43
     lai
    0.43
    лежа
    0.43
    ৩৮
    0.43
    ゴム
    0.43
    POSITIVE LOGITS
    Для
    0.55
     مسئلہ
    0.50
    Proble
    0.50
    PILE
    0.49
    О
    0.46
    Ε
    0.46
    Für
    0.44
    effer
    0.44
     построе
    0.44
    ΤΟ
    0.44
    Activations Density 0.000%

    No Known Activations