© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 15931
    Prev
    Next
    INDEX
    Explanations

    pronouns him her his her

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    唒
    1.03
    䛺
    1.01
    䍘
    1.00
    㸽
    0.96
    นะครับ
    0.95
    ោម
    0.94
    䏹
    0.92
    !!!");
    0.92
     کنیم
    0.91
    䁂
    0.91
    POSITIVE LOGITS
     mirroring
    0.80
    Di
    0.79
     Di
    0.75
    VM
    0.74
     Som
    0.73
     viol
    0.72
     Parma
    0.72
     which
    0.72
     hand
    0.70
     Av
    0.69
    Activations Density 0.005%

    No Known Activations