© 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. 108822
    Prev
    Next
    INDEX
    Explanations

    indicators with

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

    email subject lines

    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
     Martino
    0.45
    [])
    0.43
    分かり
    0.42
     duplo
    0.41
    Ұ
    0.40
    物が
    0.40
    𝟘
    0.40
    c
    0.39
    stripped
    0.39
    🤤
    0.39
    POSITIVE LOGITS
     to
    0.53
    íte
    0.52
    établir
    0.52
     손
    0.49
    ÍT
    0.48
    íti
    0.48
    ío
    0.48
     तों
    0.48
    íp
    0.48
     toit
    0.47
    Activations Density 0.000%

    No Known Activations