© 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. 98760
    Prev
    Next
    INDEX
    Explanations

    diverse languages and topics

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

    talking about teams or general statements

    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
    ıp
    0.49
     edad
    0.48
    🚆
    0.48
     поклон
    0.47
     usia
    0.47
     inescap
    0.47
     réception
    0.46
    शासित
    0.46
     ję
    0.46
     uneasy
    0.45
    POSITIVE LOGITS
    振動
    0.44
     financials
    0.44
    体が
    0.44
     "*
    0.43
    ("*
    0.43
     مشینوں
    0.43
    찻
    0.43
     సినిమాలు
    0.42
     bitcoins
    0.42
    いが
    0.42
    Activations Density 0.000%

    No Known Activations