© 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. 143637
    Prev
    Next
    INDEX
    Explanations

    jargonpanels

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

    acronyms and `for` phrases

    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
    ти
    0.46
    oin
    0.46
    ator
    0.45
    aval
    0.43
    ibe
    0.42
    频率
    0.42
    ateur
    0.41
     않
    0.41
    >&
    0.41
    ็ด
    0.40
    POSITIVE LOGITS
    dummies
    0.49
     costas
    0.48
     amigas
    0.47
     переменных
    0.47
     contraception
    0.46
     Alcat
    0.46
     Kota
    0.46
    ইসলাম
    0.45
     Sumatra
    0.45
     Интернет
    0.45
    Activations Density 0.001%

    No Known Activations