© 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. 49168
    Prev
    Next
    INDEX
    Explanations

    days of the week and themes

    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
    usional
    0.44
    ipal
    0.41
    ibular
    0.38
    큘
    0.38
    न्हें
    0.37
    schemaLocation
    0.37
     cursed
    0.37
    该
    0.37
    por
    0.37
    äle
    0.37
    POSITIVE LOGITS
     amené
    0.50
     Kins
    0.49
     ln
    0.48
     subi
    0.47
     mog
    0.47
     oblasti
    0.47
     Talks
    0.47
     ricev
    0.46
     Latitude
    0.46
     nz
    0.46
    Activations Density 0.002%

    No Known Activations