© 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. 204390
    Prev
    Next
    INDEX
    Explanations

    removing mess

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

    historical context and domain availability

    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
    🎓
    0.50
    ısında
    0.49
     пове
    0.48
     самым
    0.47
    esinde
    0.47
     diez
    0.47
     pese
    0.46
     اللغه
    0.46
     esse
    0.46
     ಆದರೆ
    0.46
    POSITIVE LOGITS
    ط
    0.48
    fing
    0.45
    治
    0.44
    Ports
    0.43
    小数
    0.43
    抒
    0.43
     बचपन
    0.42
    っきり
    0.42
     Ports
    0.41
    NUT
    0.41
    Activations Density 0.002%

    No Known Activations