© 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. 36370
    Prev
    Next
    INDEX
    Explanations

    do the same thing

    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
    렜
    0.47
     التالي
    0.46
     واللي
    0.46
    Nä
    0.44
     Oké
    0.44
    Ave
    0.44
    鸰
    0.43
     Dünya
    0.43
    Ци
    0.43
    :')
    0.42
    POSITIVE LOGITS
    iden
    0.48
    itories
    0.46
    函数的
    0.44
     chor
    0.44
    ബർ
    0.44
    istics
    0.44
    部分的
    0.42
    زان
    0.42
     architectures
    0.42
    s
    0.41
    Activations Density 0.007%

    No Known Activations