© 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. 16-GEMMASCOPE-2-RES-65K
    7. 167
    Prev
    Next
    INDEX
    Explanations

    this followed by a noun

    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_16_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
    де
    0.35
    bí
    0.31
    បញ្ចប់
    0.31
    ス
    0.31
    бил
    0.31
    Į
    0.31
    ደን
    0.30
     αλλά
    0.30
    рано
    0.29
    дят
    0.29
    POSITIVE LOGITS
    0.37
    ;
    0.32
    har
    0.27
    ipe
    0.26
    han
    0.26
    i
    0.26
    iu
    0.25
    </u>
    0.25
    І
    0.25
     Psychology
    0.25
    Activations Density 0.312%

    No Known Activations