© 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. 29-GEMMASCOPE-2-RES-16K
    7. 3944
    Prev
    Next
    INDEX
    Explanations

    placeholders following "your"

    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_29_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     itself
    0.85
     soprattutto
    0.85
     anyone
    0.85
     you
    0.82
     verhindern
    0.81
     ​​
    0.78
     zich
    0.78
     everyone
    0.77
    ️
    0.77
     their
    0.77
    POSITIVE LOGITS
     own
    1.73
     Own
    1.58
    Own
    1.35
     favorite
    1.31
     favourite
    1.25
     eigenes
    1.25
     Highness
    1.23
    SELF
    1.15
    favorite
    1.12
    sef
    1.12
    Activations Density 0.146%

    No Known Activations