© 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. 14936
    Prev
    Next
    INDEX
    Explanations

    crisis helplines

    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
     delicious
    1.30
     tasty
    1.26
     daging
    1.24
     microbes
    1.24
     versatile
    1.18
     tagline
    1.16
    Ϊ
    1.16
    𝙍
    1.15
     drape
    1.14
    CuO
    1.14
    POSITIVE LOGITS
     психи
    1.88
     psych
    1.81
     психо
    1.78
     psychiatric
    1.73
     psychotherapy
    1.67
    心理
    1.66
     Psych
    1.66
    psych
    1.63
     মানসিক
    1.61
     psich
    1.61
    Activations Density 0.300%

    No Known Activations