© 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. 66
    Prev
    Next
    INDEX
    Explanations

    decisions related

    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
    <unused1735>
    0.45
    <unused937>
    0.45
     Trabal
    0.43
    <unused2063>
    0.43
    <unused275>
    0.42
    <unused295>
    0.42
     difficol
    0.42
    <unused289>
    0.42
     Comple
    0.42
     Internation
    0.41
    POSITIVE LOGITS
     Blood
    0.82
    Blood
    0.78
     
    0.76
     Symptoms
    0.74
     .
    0.67
     BLOOD
    0.67
     blood
    0.66
     Low
    0.63
     What
    0.60
     Signs
    0.59
    Activations Density 0.139%

    No Known Activations