© 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. 188023
    Prev
    Next
    INDEX
    Explanations

    looking for specific phrases

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

    switch providers

    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
    tiene
    0.50
    友達
    0.48
    contenido
    0.47
    Convolution
    0.47
    ni
    0.47
    dominated
    0.46
    n
    0.45
    뜨
    0.45
    ée
    0.45
    min
    0.44
    POSITIVE LOGITS
     duyg
    0.55
     primaryStage
    0.51
     cfp
    0.50
     viktig
    0.49
     İng
    0.49
     sağlı
    0.49
     generalizes
    0.49
    وڈ
    0.49
     bodybuilding
    0.48
     bilgis
    0.48
    Activations Density 0.000%

    No Known Activations