© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 159323
    Prev
    Next
    INDEX
    Explanations

    foreign or listing phrases

    np_acts-logits-general · gemini-2.5-flash-lite

    relief from suffering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    INDE
    0.45
     datth
    0.45
    িপ্ত
    0.44
    \|,
    0.43
    !»
    0.43
    !),
    0.42
     Dobson
    0.42
     вчера
    0.42
    يح
    0.41
    !।
    0.41
    POSITIVE LOGITS
     자동으로
    0.46
    reshold
    0.44
    正
    0.42
    外国
    0.41
    来店
    0.41
    瓒
    0.40
    负
    0.40
    MgCl
    0.39
    illance
    0.38
    ρε
    0.38
    Activations Density 0.000%

    No Known Activations