© 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. 187974
    Prev
    Next
    INDEX
    Explanations

    gold settings

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

    lists and categories

    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
     который
    0.51
    ਟ
    0.48
     দিলে
    0.46
     ਅਤੇ
    0.46
     सुद्धा
    0.46
     आमिर
    0.45
     който
    0.45
     desempe
    0.45
     которую
    0.44
     desempen
    0.44
    POSITIVE LOGITS
    MH
    0.46
    ^{\
    0.44
    _{
    0.44
     identical
    0.43
     mathvariant
    0.42
    gkin
    0.42
    PHI
    0.42
     chronically
    0.41
     reported
    0.41
     analogous
    0.41
    Activations Density 0.001%

    No Known Activations