© 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. 97954
    Prev
    Next
    INDEX
    Explanations

    has been or has dimension

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

    not X but Y

    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
     Oldborough
    0.49
    中华人民共和国
    0.47
    萍
    0.46
    ändige
    0.45
     इट
    0.43
     Iterable
    0.42
     tepl
    0.42
     事
    0.41
     svě
    0.41
     ফরজ
    0.41
    POSITIVE LOGITS
     戦
    0.48
     または
    0.47
    瀟
    0.46
    ような
    0.44
     및
    0.43
    만한
    0.43
     さん
    0.42
     داستان
    0.42
     destroyer
    0.42
     シルバー
    0.42
    Activations Density 0.001%

    No Known Activations