© 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. 68280
    Prev
    Next
    INDEX
    Explanations

    text followed by specific nouns

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

    academic and technical subjects

    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
    щее
    0.45
    ￭
    0.44
     యొక్క
    0.43
    জ্জিত
    0.42
    houette
    0.42
    ántico
    0.42
    网址
    0.41
    趋势
    0.41
    ۹
    0.41
    rates
    0.41
    POSITIVE LOGITS
     bitch
    0.49
     accredited
    0.44
     Lle
    0.44
     Lind
    0.43
     Japanese
    0.43
    編集
    0.42
     cystic
    0.42
     bullshit
    0.41
     feed
    0.41
     shit
    0.41
    Activations Density 0.000%

    No Known Activations