© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 145398
    Prev
    Next
    INDEX
    Explanations

    numeric strings and Phoenician alphabet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     représentation
    0.52
     realising
    0.51
    ᓯ
    0.50
    학생
    0.48
    াস্থ্যের
    0.47
     recognising
    0.46
     Vegas
    0.45
     rumoured
    0.44
    騫
    0.44
     paler
    0.43
    POSITIVE LOGITS
    s
    0.54
    r
    0.53
    "]
    0.52
    "
    0.51
    of
    0.50
    DEF
    0.49
    IC
    0.49
    OF
    0.49
    ZE
    0.49
    み
    0.48
    Activations Density 0.000%

    No Known Activations