© 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. 4593
    Prev
    Next
    INDEX
    Explanations

    I + verb

    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
    Not in Any Lists

    No Comments

    Negative Logits
     to
    0.36
     אי
    0.34
     the
    0.33
     de
    0.32
     he
    0.31
     ihe
    0.30
    u
    0.30
     copies
    0.30
     argon
    0.30
     they
    0.30
    POSITIVE LOGITS
    8
    0.39
    7
    0.37
    的角色
    0.34
    的可能性
    0.30
    4
    0.30
     хватает
    0.30
    5
    0.29
    9
    0.28
    的有
    0.28
    бычно
    0.27
    Activations Density 0.576%

    No Known Activations