© 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. 11773
    Prev
    Next
    INDEX
    Explanations

    phone numbers or codes

    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
    ة
    0.41
     Established
    0.39
     regard
    0.39
    个
    0.38
    此时
    0.36
     fifth
    0.36
     frecuentes
    0.35
     참고
    0.35
     चे
    0.35
     astounding
    0.35
    POSITIVE LOGITS
    Coc
    0.47
    TEGER
    0.46
    ‍♀️
    0.46
    UCLEAR
    0.45
    CMS
    0.44
    Care
    0.43
    SMS
    0.43
    Bali
    0.43
    CCA
    0.42
    Carte
    0.42
    Activations Density 0.010%

    No Known Activations