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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 17107
    Prev
    Next
    INDEX
    Explanations

    common phrases and comparisons

    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_65k_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
     местности
    0.51
     монет
    0.45
     व्यंजन
    0.45
     جيم
    0.44
     ምክንያ
    0.42
     Brus
    0.42
    鎏
    0.42
     امرأة
    0.42
    jur
    0.41
     проду
    0.41
    POSITIVE LOGITS
    accumulation
    0.57
    retto
    0.48
    vega
    0.47
    icosa
    0.47
    iin
    0.46
    uhe
    0.46
     کمار
    0.46
    ỗ
    0.45
     meno
    0.45
     kinerja
    0.45
    Activations Density 0.011%

    No Known Activations