© 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. 120771
    Prev
    Next
    INDEX
    Explanations

    daily chapter of piece

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

    struggles, inaudible, fighting, fear, Kyiv

    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
     органами
    0.47
     एहसास
    0.47
     गौर
    0.46
     ե
    0.46
     રો
    0.45
     зві
    0.44
     ಹ
    0.44
     ખ
    0.44
     fillets
    0.43
    ियर
    0.43
    POSITIVE LOGITS
    多种
    0.52
    Characteristic
    0.46
    وش
    0.46
    мя
    0.46
     mitten
    0.45
    nica
    0.44
    ్రియ
    0.44
    raster
    0.44
    myItemType
    0.44
    ""
    0.43
    Activations Density 0.001%

    No Known Activations