© 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. 37005
    Prev
    Next
    INDEX
    Explanations

    plaza names

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

    sequence generation

    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
     wund
    0.45
    ú
    0.45
    e
    0.44
     liquides
    0.42
    ered
    0.41
    այն
    0.41
     aston
    0.41
     registrant
    0.40
    biz
    0.40
    itelji
    0.40
    POSITIVE LOGITS
    📕
    0.46
     একদিকে
    0.45
    QUARE
    0.45
     Qin
    0.44
     Acting
    0.44
    !!!!!!
    0.43
    ডো
    0.43
     Sequencing
    0.43
     pyplot
    0.43
    の時間
    0.43
    Activations Density 0.000%

    No Known Activations