© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 46484
    Prev
    Next
    INDEX
    Explanations

    seeking help for harmful thoughts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
    煥
    0.44
     humide
    0.44
     KAHN
    0.43
    ຫຼາຍ
    0.43
    授权
    0.40
     BELOW
    0.40
    卖家
    0.40
     Kwon
    0.39
    埝
    0.39
     करवाई
    0.39
    POSITIVE LOGITS
     |
    0.41
    enburg
    0.35
    ]])
    0.34
    <sup>
    0.33
    )]
    0.33
    \
    0.33
    muş
    0.32
    .\
    0.32
     Niederlande
    0.31
     (
    0.31
    Activations Density 0.006%

    No Known Activations