© 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. 13-GEMMASCOPE-2-RES-16K
    7. 5968
    Prev
    Next
    INDEX
    Explanations

    mental health support

    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
    月号
    1.29
    ちゃう
    1.28
    EDULE
    1.25
    ᒪ
    1.22
    𝙉
    1.19
     Verfügung
    1.16
    Scorch
    1.16
    diendo
    1.16
    elizmente
    1.15
    ナソニック
    1.15
    POSITIVE LOGITS
    ers
    1.42
    akor
    1.24
    с
    1.16
    zás
    1.13
     UPS
    1.12
    ハン
    1.12
    iban
    1.12
    懸
    1.08
    asi
    1.07
    м
    1.07
    Activations Density 0.102%

    No Known Activations