© 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. 168524
    Prev
    Next
    INDEX
    Explanations

    right to

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

    not necessarily, demonstrate that, understanding how

    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
     तैयारियां
    0.47
    |।
    0.47
     mostrado
    0.47
    schemaName
    0.47
    病例
    0.46
     prípade
    0.46
     procé
    0.45
     පිළිබඳ
    0.45
    inputStream
    0.44
     matemático
    0.44
    POSITIVE LOGITS
     t
    0.61
     ko
    0.49
     lub
    0.49
     et
    0.48
     han
    0.48
     n
    0.47
     Award
    0.46
     award
    0.46
     trop
    0.46
     loved
    0.45
    Activations Density 0.001%

    No Known Activations