© 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. 244162
    Prev
    Next
    INDEX
    Explanations

    got a, have a, contains evaluation

    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
    籙
    0.53
    ديث
    0.50
    િટ
    0.47
     matematica
    0.47
    毓
    0.47
    헐
    0.47
     Closure
    0.46
    Closure
    0.46
     Ст
    0.46
    리티
    0.46
    POSITIVE LOGITS
     l
    0.50
    }/\
    0.48
     and
    0.48
    walt
    0.47
     survivor
    0.47
    l
    0.46
     다음과
    0.46
     iceberg
    0.46
     nich
    0.46
     están
    0.45
    Activations Density 0.000%

    No Known Activations