© 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. 105760
    Prev
    Next
    INDEX
    Explanations

    largest installment

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

    Loss, separation, shape, goals

    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
     SCO
    0.49
     BUT
    0.49
     SOME
    0.48
     thanked
    0.47
     ALL
    0.46
    ब
    0.45
     HIT
    0.44
    ✌
    0.44
     ENV
    0.44
     HO
    0.43
    POSITIVE LOGITS
     तस्करी
    0.49
     theorems
    0.47
    ímetros
    0.46
    atiable
    0.45
     automatiquement
    0.44
     semasa
    0.43
     गिनती
    0.43
     هستند
    0.43
    Bokeh
    0.43
    这两个
    0.43
    Activations Density 0.000%

    No Known Activations