© 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. 63870
    Prev
    Next
    INDEX
    Explanations

    soaked tissues

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

    commands and permissions

    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
    ?
    0.47
    ...?
    0.46
    ٬
    0.44
     пайда
    0.43
    프트
    0.43
     jeszcze
    0.43
    _
    0.42
    ？
    0.42
    は
    0.41
    )?
    0.41
    POSITIVE LOGITS
    elyn
    0.48
    änglich
    0.48
    inse
    0.44
    egen
    0.44
     आतंकवादी
    0.43
     criminals
    0.42
     పోలీ
    0.42
    attham
    0.42
    aughty
    0.42
     एडी
    0.42
    Activations Density 0.000%

    No Known Activations