© 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. 218741
    Prev
    Next
    INDEX
    Explanations

    price tag

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

    non-latin characters

    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
     noise
    0.51
    s
    0.51
     friendship
    0.50
     Jon
    0.49
     level
    0.48
     queue
    0.48
    d
    0.48
     progress
    0.47
     scale
    0.47
     frustration
    0.47
    POSITIVE LOGITS
     গাড়ী
    0.55
     кеңсеси
    0.55
     गुलाबी
    0.54
    bindingFields
    0.52
    コンビニ
    0.52
    キ
    0.52
    уна
    0.51
    𝘬
    0.51
    ほとんど
    0.51
    材質
    0.50
    Activations Density 0.001%

    No Known Activations