© 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. 129296
    Prev
    Next
    INDEX
    Explanations

    names or titles followed by descriptions

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

    series, blog, tutorial, time, tech, perspective

    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
    >-</
    0.52
     进入
    0.52
     switchTo
    0.49
    しており
    0.45
     説明
    0.45
     單
    0.45
     ตาย
    0.45
     delaying
    0.44
     mỗi
    0.43
     ખે
    0.43
    POSITIVE LOGITS
    Message
    0.52
     BLE
    0.49
    Adress
    0.49
     Isle
    0.48
    Newsletter
    0.48
    Qa
    0.48
    Occurrence
    0.48
    聒
    0.48
     WER
    0.47
     Courier
    0.47
    Activations Density 0.000%

    No Known Activations