© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 945
    Prev
    Next
    INDEX
    Explanations

    wikipedia urls and code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     c
    0.63
    을
    0.62
     f
    0.62
     -
    0.62
    캔
    0.61
      
    0.60
    를
    0.58
     covered
    0.58
    <0xC2>
    0.57
     conversation
    0.57
    POSITIVE LOGITS
     indestruct
    0.81
    Trajectories
    0.80
     മിക
    0.77
    юнча
    0.77
    Literatur
    0.76
    jahteraan
    0.76
     ازيكم
    0.76
    ostridium
    0.75
    lusconi
    0.75
    หล่ง
    0.73
    Activations Density 0.189%

    No Known Activations