© 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. 161241
    Prev
    Next
    INDEX
    Explanations

    shall not be liable

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

    psychiatrists approach

    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
     deut
    0.54
    )\
    0.52
     Combine
    0.51
     Devils
    0.50
     Maur
    0.50
     süd
    0.50
     次
    0.49
     nächste
    0.49
     hole
    0.48
     combinación
    0.48
    POSITIVE LOGITS
    ני
    0.51
    我有
    0.51
    snippet
    0.47
    universal
    0.47
    𝘦
    0.46
    svg
    0.45
     אני
    0.45
    bukti
    0.45
    𝘶
    0.45
    gente
    0.44
    Activations Density 0.002%

    No Known Activations