© 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. 195987
    Prev
    Next
    INDEX
    Explanations

    standardized in

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

    after punctuation

    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
    செ
    0.49
     Según
    0.46
     janela
    0.45
     aproximadamente
    0.44
    ғ
    0.44
     уж
    0.43
    િલે
    0.43
     según
    0.43
    ટ્સ
    0.43
    ╾
    0.43
    POSITIVE LOGITS
    hary
    0.52
    are
    0.51
    รุ่น
    0.48
     =>
    0.47
    rs
    0.47
     defaulting
    0.45
    .");
    0.45
    คณะ
    0.45
    default
    0.44
    wati
    0.44
    Activations Density 0.001%

    No Known Activations