© 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. 20852
    Prev
    Next
    INDEX
    Explanations

    just followed by quotation or if

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

    existence and well-being

    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
     فعال
    0.44
     увеличи
    0.43
    ("*
    0.42
    će
    0.40
    krét
    0.40
     legitimately
    0.40
    েত্রে
    0.40
     classed
    0.40
    PerPage
    0.39
    有害
    0.39
    POSITIVE LOGITS
    dont
    0.50
    。
    0.49
    does
    0.47
     sukh
    0.46
    to
    0.46
    سین
    0.46
     siitä
    0.45
    ੀ
    0.45
    washington
    0.44
    ിട
    0.43
    Activations Density 0.000%

    No Known Activations