© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 9390
    Prev
    Next
    INDEX
    Explanations

    mental health

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_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
    <h3>
    1.21
    </td>
    1.04
    <h2>
    1.02
    </h1>
    0.97
    </h3>
    0.97
    ัย
    0.95
    вере
    0.93
    <h4>
    0.92
    </h6>
    0.92
    යක
    0.84
    POSITIVE LOGITS
     Lax
    0.89
     hasil
    0.86
     Basics
    0.84
     Hacker
    0.81
     lâm
    0.79
    控え
    0.79
     lutte
    0.79
    stool
    0.78
     Kid
    0.76
     Nutr
    0.75
    Activations Density 0.003%

    No Known Activations