© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 235786
    Prev
    Next
    INDEX
    Explanations

    location descriptions

    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
     stockno
    0.53
    মেজ
    0.45
    भीर
    0.44
     accedi
    0.43
    क्टेयर
    0.43
     gerne
    0.43
    quefois
    0.43
    𝒟
    0.43
    ophy
    0.42
    𝔰
    0.42
    POSITIVE LOGITS
     Galveston
    0.46
     Breton
    0.46
    أ
    0.46
     за
    0.44
    罍
    0.43
    ي
    0.43
     ко
    0.42
     ма
    0.42
    М
    0.42
     Benito
    0.41
    Activations Density 0.000%

    No Known Activations