© 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. 109434
    Prev
    Next
    INDEX
    Explanations

    venues and performers

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

    providing examples or explanations

    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
    HOT
    0.54
    rı
    0.50
    eight
    0.50
    它
    0.49
    ele
    0.49
    leme
    0.48
    pá
    0.47
    COP
    0.47
    {
    0.47
    ponden
    0.47
    POSITIVE LOGITS
     あれ
    0.46
     Ains
    0.46
     Karena
    0.45
     Antis
    0.45
    ックス
    0.45
     Selig
    0.45
     Adapun
    0.45
     Section
    0.44
     *"
    0.44
     hardships
    0.43
    Activations Density 0.001%

    No Known Activations