© 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. 106160
    Prev
    Next
    INDEX
    Explanations

    articles followed by specific nouns

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

    explaining or defining concepts

    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
    狰
    0.46
     സൃഷ്ട
    0.46
    ২৬
    0.45
    但他
    0.43
    ईद
    0.42
     enshr
    0.42
    해야
    0.41
     därför
    0.41
     Nonetheless
    0.41
     nonetheless
    0.40
    POSITIVE LOGITS
    ’
    0.48
     jumped
    0.45
     pozitiv
    0.45
     oprav
    0.44
    peat
    0.43
     similar
    0.43
     }}
    0.43
     хле
    0.43
    と同様
    0.42
     diarias
    0.42
    Activations Density 0.000%

    No Known Activations