© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5546
    Prev
    Next
    INDEX
    Explanations

    Substance Abuse and Mental Health Services Administration

    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_13_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
    adang
    0.98
    ak
    0.97
    ent
    0.96
    anth
    0.92
    ip
    0.92
    aren
    0.88
    kun
    0.87
    '
    0.86
    ith
    0.86
    prima
    0.85
    POSITIVE LOGITS
     CMV
    1.48
     GLE
    1.46
     `>`,
    1.43
     Cé
    1.43
     COD
    1.41
     MOV
    1.41
     SEL
    1.40
     JSX
    1.39
     startled
    1.38
     `:`
    1.37
    Activations Density 0.138%

    No Known Activations