© 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. 187024
    Prev
    Next
    INDEX
    Explanations

    Continuing to

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

    here to help

    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
    죠
    0.45
    కీయ
    0.44
     whopping
    0.41
    活性
    0.41
    )').
    0.40
    حث
    0.40
    äss
    0.39
     BUN
    0.39
    )”.
    0.39
     dev
    0.39
    POSITIVE LOGITS
     ili
    0.57
    ၊
    0.54
    𝗕
    0.52
     או
    0.51
     מפ
    0.51
     tavolo
    0.51
     acuerdo
    0.51
    Mp
    0.50
    TableAdapter
    0.50
     доступа
    0.49
    Activations Density 0.000%

    No Known Activations