© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 195702
    Prev
    Next
    INDEX
    Explanations

    predictive AI

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

    Originally, Minimize, integrated

    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
     gráf
    0.54
    ജീ
    0.46
     പിറ
    0.46
     haja
    0.44
    రూ
    0.44
    闿
    0.43
     Satz
    0.43
    ங்கிணை
    0.43
     sahip
    0.43
    fle
    0.42
    POSITIVE LOGITS
    ギリス
    0.50
    ingress
    0.46
     نہیں۔
    0.45
    在你
    0.45
    LIN
    0.45
     произведения
    0.45
    ँ
    0.45
    oriya
    0.44
     chains
    0.44
     νέ
    0.44
    Activations Density 0.001%

    No Known Activations