© 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. 5775
    Prev
    Next
    INDEX
    Explanations

    date formats

    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
     роли
    0.44
    ßen
    0.42
     سال
    0.41
     den
    0.40
     ใบ
    0.39
     философ
    0.38
    _{-}\
    0.38
    ẞ
    0.38
     основа
    0.37
     velit
    0.37
    POSITIVE LOGITS
    includ
    0.40
    classteacher
    0.39
    ারে
    0.38
    urgery
    0.37
     imagina
    0.37
    φαν
    0.36
     sweeter
    0.35
    elink
    0.35
     快
    0.35
     backyard
    0.35
    Activations Density 0.032%

    No Known Activations