© 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. 251730
    Prev
    Next
    INDEX
    Explanations

    call to action phrases

    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
    우
    0.52
     успеха
    0.51
    нова
    0.51
    ब्र
    0.50
    ਹ
    0.50
    브
    0.50
    ૢ
    0.49
    λέ
    0.49
    ইন
    0.49
    Aby
    0.49
    POSITIVE LOGITS
    ina
    0.57
    ih
    0.54
    ii
    0.54
    cu
    0.54
    ra
    0.53
    pe
    0.52
    ie
    0.51
    la
    0.50
    berg
    0.49
    bert
    0.48
    Activations Density 0.001%

    No Known Activations