© 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. 224769
    Prev
    Next
    INDEX
    Explanations

    don't be nervous

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

    specific details and terms

    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
    \
    0.54
    ре
    0.52
    ல
    0.52
    br
    0.51
    lt
    0.49
    usually
    0.48
    window
    0.48
    я
    0.48
    ாவது
    0.47
    @
    0.47
    POSITIVE LOGITS
     specifiche
    0.57
     Sema
    0.52
     ટીમ
    0.52
     Employment
    0.51
     ഇക്കാര
    0.50
     devemos
    0.50
     Vedi
    0.50
     кеңселер
    0.50
     GÉN
    0.50
     INSTALL
    0.50
    Activations Density 0.001%

    No Known Activations