© 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. 49444
    Prev
    Next
    INDEX
    Explanations

    pain, legal, slightly

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

    extracting information or describing possibilities

    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
     cartridges
    0.51
    //!
    0.48
    ‑
    0.45
     necessari
    0.44
    GoogleApiClient
    0.44
    hah
    0.43
     nationals
    0.43
     affiliates
    0.43
    //#
    0.42
     dashboards
    0.42
    POSITIVE LOGITS
    ë
    0.48
     ২৭
    0.48
     времен
    0.47
     TED
    0.46
    рэ
    0.44
     武田
    0.44
    ków
    0.44
     THF
    0.44
     Très
    0.43
     TIC
    0.43
    Activations Density 0.000%

    No Known Activations