© 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. 170206
    Prev
    Next
    INDEX
    Explanations

    moving services and guides

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

    structured courses

    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
    --"
    0.52
    ?'
    0.50
    --’
    0.48
     Aşağı
    0.47
     istraž
    0.47
     araşt
    0.46
    ifikasi
    0.46
    LAGS
    0.46
    )-$
    0.46
    EIS
    0.46
    POSITIVE LOGITS
    ld
    0.47
     thine
    0.46
     cracks
    0.44
     सेंट
    0.43
     Beacon
    0.43
     supporter
    0.42
    सरत
    0.41
    ktx
    0.41
     fireman
    0.41
     supporters
    0.40
    Activations Density 0.000%

    No Known Activations