© 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. 158220
    Prev
    Next
    INDEX
    Explanations

    handle for, lot based, parking area, agency, records sufficient, depending on, son or

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

    suits, duties, rect

    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
    maligngroup
    0.51
    㐹
    0.50
    チャン
    0.50
    fcntl
    0.47
     ながら
    0.47
    encrypt
    0.47
     FRANCISCO
    0.46
    .??.??"]
    0.45
    アル
    0.44
     कब्र
    0.44
    POSITIVE LOGITS
     evoked
    0.46
    俅
    0.44
    Born
    0.43
    俘
    0.42
     Pelosi
    0.41
     daño
    0.41
    浙
    0.41
    欺
    0.41
     hemod
    0.40
    Bir
    0.40
    Activations Density 0.001%

    No Known Activations