© 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. 160745
    Prev
    Next
    INDEX
    Explanations

    backyard garden

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

    attic, setting, literary, days

    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
     endowed
    0.52
    u
    0.48
    এম
    0.47
     reusing
    0.47
     inquiring
    0.45
    м
    0.45
     reú
    0.44
    $\
    0.44
     Lord
    0.44
     inquired
    0.44
    POSITIVE LOGITS
    hető
    0.45
     வடிவ
    0.44
     방식
    0.44
    Jdk
    0.41
    tsó
    0.41
     stagn
    0.41
    جل
    0.40
    ổi
    0.40
     ფორ
    0.40
    alakip
    0.40
    Activations Density 0.000%

    No Known Activations