© 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. 3068
    Prev
    Next
    INDEX
    Explanations

    scientific terms and concepts

    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
    ujourd
    0.39
    )，
    0.38
    ل
    0.38
    스
    0.37
    ల్
    0.37
    것
    0.37
    이나
    0.37
    And
    0.36
     informática
    0.36
    л
    0.36
    POSITIVE LOGITS
     phosphorylation
    0.40
    従って
    0.39
     M
    0.39
     F
    0.38
     Besonder
    0.38
     ACO
    0.36
     ELISA
    0.36
     NEVER
    0.34
     SNC
    0.34
     ISO
    0.34
    Activations Density 0.423%

    No Known Activations