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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 6694
    Prev
    Next
    INDEX
    Explanations

    saying something:

    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
    টাতে
    0.49
    ■
    0.42
     callers
    0.42
     terhadap
    0.40
     expressed
    0.38
     खेलकर
    0.38
     putative
    0.37
     ostensibly
    0.36
     තුළ
    0.36
     seus
    0.36
    POSITIVE LOGITS
     YES
    0.61
     yes
    0.60
     "!
    0.57
    :
    0.56
    :“
    0.56
    yes
    0.55
    :”
    0.55
    ：“
    0.54
     "¿
    0.53
     ‘
    0.52
    Activations Density 0.079%

    No Known Activations