© 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. 129
    Prev
    Next
    INDEX
    Explanations

    mental health helplines

    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
     ▪
    0.96
     emble
    0.94
     ʼ
    0.93
     Frankenstein
    0.93
     dystopian
    0.90
     colloqu
    0.90
     Lollipop
    0.89
     feudal
    0.88
     Fortuna
    0.88
     figurines
    0.88
    POSITIVE LOGITS
    {\
    2.26
    \
    1.78
     {\
    1.67
    *{\
    1.61
    {{\
    1.59
     \
    1.53
    *\
    1.50
    %\
    1.32
    ={\
    1.31
    \{\
    1.30
    Activations Density 0.009%

    No Known Activations