© 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. 198110
    Prev
    Next
    INDEX
    Explanations

    Spanish for chirping

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

    querySelector, newline, nested list

    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
     renamed
    0.49
     Corporate
    0.47
     owned
    0.47
    ﮯ
    0.46
     replicated
    0.45
    蝌
    0.44
     revital
    0.44
     nicknamed
    0.43
     rental
    0.42
    と呼ば
    0.42
    POSITIVE LOGITS
    编辑器
    0.46
    édition
    0.45
    esy
    0.45
     خاطر
    0.44
     chưa
    0.43
    examin
    0.43
    ე
    0.42
     examiners
    0.42
     तपास
    0.42
    FilePath
    0.41
    Activations Density 0.000%

    No Known Activations