© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 8684
    Prev
    Next
    INDEX
    Explanations

    Line-by-line explanations or programming separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    a
    0.53
    ։
    0.53
     entirely
    0.46
     про
    0.44
    ↵↵
    0.44
    ⟩
    0.44
     Skinner
    0.43
    ᱾
    0.43
    penup
    0.42
    blur
    0.42
    POSITIVE LOGITS
     argc
    0.66
    同學們
    0.65
    猁
    0.62
    vaegir
    0.61
    থানি
    0.60
     numpy
    0.60
     나가
    0.59
    ლ
    0.59
     患者
    0.58
     pacientes
    0.58
    Activations Density 0.000%

    No Known Activations