© 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. 51239
    Prev
    Next
    INDEX
    Explanations

    gratitude after animal mention

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

    visualize or threats or struggled or medical

    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
    ра
    0.58
    ята
    0.54
    涳
    0.54
    பின்னர்
    0.54
    цене
    0.53
    д
    0.53
    Су
    0.52
     évaluations
    0.52
    су
    0.51
    оте
    0.50
    POSITIVE LOGITS
    ServiceClient
    0.54
     was
    0.50
     Fung
    0.47
     a
    0.47
    hh
    0.46
     basalt
    0.46
     kun
    0.45
     Surgical
    0.45
     autoch
    0.43
    tt
    0.43
    Activations Density 0.000%

    No Known Activations