© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2084
    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-2-4b-it/resid_post/layer_9_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
    dere
    2.51
    are
    2.42
     Есть
    2.37
    íc
    2.21
    ${
    2.20
     nothing
    2.16
    nothing
    2.15
    दार
    2.13
    ]));
    2.10
     gelap
    2.08
    POSITIVE LOGITS
    ت
    3.27
    ر
    2.94
    म
    2.74
    т
    2.68
    इस
    2.68
    夂
    2.61
    ট
    2.57
    ıları
    2.56
     মতি
    2.54
    ſelf
    2.53
    Activations Density 0.555%

    No Known Activations