© 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. 4088
    Prev
    Next
    INDEX
    Explanations

    how to / questions

    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
     ܕ
    0.40
    投稿
    0.38
     abandon
    0.38
     alot
    0.37
    放弃
    0.37
     تحفظ
    0.37
    اران
    0.36
    fos
    0.36
    arov
    0.36
     hann
    0.36
    POSITIVE LOGITS
    ્યું
    0.43
    ્યાં
    0.38
    кци
    0.36
    笾
    0.36
     olympi
    0.36
    oljš
    0.35
     Procedures
    0.35
     Denial
    0.35
    ប់
    0.34
     discretized
    0.34
    Activations Density 0.000%

    No Known Activations