© 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. 26503
    Prev
    Next
    INDEX
    Explanations

    starts phrases with common words

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

    preceding phrases

    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
     Primero
    0.51
     サイ
    0.50
    čila
    0.48
     フラワー
    0.47
     ナイ
    0.46
    uestro
    0.46
     सरी
    0.46
     カ
    0.46
    SERVICIO
    0.46
     ඇති
    0.44
    POSITIVE LOGITS
    躡
    0.46
     radius
    0.46
     slits
    0.46
     γ
    0.46
     gamma
    0.45
    两位
    0.44
     ভীত
    0.44
     Trapez
    0.44
    νά
    0.44
     memorabilia
    0.42
    Activations Density 0.000%

    No Known Activations