© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 56998
    Prev
    Next
    INDEX
    Explanations

    angry or upset

    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
     Dick
    0.48
     huyền
    0.46
     Ро
    0.44
    Dick
    0.44
    х
    0.44
     क्वांटिटी
    0.43
    ԝ
    0.43
     процесса
    0.42
    :”
    0.42
     Кор
    0.40
    POSITIVE LOGITS
    em
    0.54
    am
    0.51
    uj
    0.44
    clonal
    0.44
    lEdit
    0.44
    uz
    0.44
    leq
    0.44
    ubmit
    0.44
    clamp
    0.43
    prüfung
    0.43
    Activations Density 0.005%

    No Known Activations