© 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. 169927
    Prev
    Next
    INDEX
    Explanations

    quantity, time, scope

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

    encyclopedia, violence, device standards

    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
     ملت
    0.44
     فائ
    0.43
     وآ
    0.41
     vụ
    0.41
     والإ
    0.40
    .
    0.40
    ።
    0.40
    吐槽
    0.39
     وتق
    0.39
     قالت
    0.39
    POSITIVE LOGITS
     instrumentos
    0.50
    ethoven
    0.48
     enfermedades
    0.47
     strumenti
    0.47
     दवाई
    0.47
    ολ
    0.46
     Trag
    0.46
     Scientists
    0.46
    氈
    0.46
    ildiği
    0.45
    Activations Density 0.002%

    No Known Activations