© 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. 171910
    Prev
    Next
    INDEX
    Explanations

    chosen to share

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

    comparisons and states

    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
    Negative Logits
    бля
    0.51
    ترح
    0.49
     grids
    0.48
    akuan
    0.46
    аб
    0.45
    роб
    0.44
     fleets
    0.44
     clashes
    0.44
    呆
    0.44
    ак
    0.43
    POSITIVE LOGITS
    Value
    0.48
     Điện
    0.47
    Changes
    0.45
    Btn
    0.45
     από
    0.44
     αί
    0.44
     നേര
    0.43
    ValueOf
    0.43
     همچنین
    0.42
    ISource
    0.42
    Activations Density 0.001%

    No Known Activations