© 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. 136672
    Prev
    Next
    INDEX
    Explanations

    unmarried mothers, therapy, psychotherapy

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

    favorable reaction

    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
    εια
    0.52
     selección
    0.47
     ö
    0.45
    éclair
    0.44
    蛭
    0.44
    灭
    0.44
    就已经
    0.43
     burgundy
    0.43
     všetky
    0.43
    銠
    0.43
    POSITIVE LOGITS
     unmarried
    0.47
    therapy
    0.46
    binghamton
    0.45
     samaj
    0.45
     স্কুলে
    0.44
    n
    0.44
    simplified
    0.43
     Performs
    0.43
     jailed
    0.42
     psychotherapy
    0.42
    Activations Density 0.000%

    No Known Activations