© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 52474
    Prev
    Next
    INDEX
    Explanations

    descriptive words and labels

    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
     exciting
    0.51
    ایی
    0.48
    im
    0.48
    /
    0.48
    izer
    0.47
     wanting
    0.46
    Am
    0.45
     libertarian
    0.45
    acerb
    0.45
     and
    0.45
    POSITIVE LOGITS
     OFFICES
    0.56
     fós
    0.54
     IGN
    0.53
     Ró
    0.52
     školy
    0.52
    ômios
    0.50
     PAGE
    0.50
    憊
    0.49
     strán
    0.48
     getN
    0.48
    Activations Density 0.015%

    No Known Activations