© 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-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14749
    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-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rumours
    1.30
     finalised
    1.20
    ၡ
    1.16
     nonlinearity
    1.11
     atrocious
    1.11
     hapless
    1.10
     সাড়ে
    1.09
     realtime
    1.09
     despatch
    1.08
    કિસ્
    1.08
    POSITIVE LOGITS
    -
    0.95
    ople
    0.87
     "$
    0.75
    st
    0.74
     -
    0.73
    nya
    0.72
    ாவ
    0.71
    mma
    0.69
    पटा
    0.69
    "-
    0.66
    Activations Density 0.008%

    No Known Activations