© 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. 156460
    Prev
    Next
    INDEX
    Explanations

    related products

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

    explaining options or core components

    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
    ᱗
    0.47
     ထ
    0.46
     συνο
    0.44
    用の
    0.44
     motive
    0.41
     대응
    0.40
     transpose
    0.40
     bulging
    0.39
     წ
    0.39
     upheaval
    0.39
    POSITIVE LOGITS
    рма
    0.50
    OW
    0.47
    Ṛ
    0.47
    ंवर
    0.46
     хуже
    0.45
    澳门
    0.45
    ੂ
    0.44
    ॉस
    0.43
     शिलालेख
    0.43
    Waste
    0.43
    Activations Density 0.002%

    No Known Activations