© 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. 7075
    Prev
    Next
    INDEX
    Explanations

    primality of even numbers

    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
     Calculate
    0.38
    ቆ
    0.38
    EO
    0.37
     nal
    0.37
    ଲେ
    0.37
     groupby
    0.37
    ቈ
    0.36
    で行
    0.36
    rst
    0.36
     Chỉ
    0.36
    POSITIVE LOGITS
     like
    0.41
     ширина
    0.41
     diminutive
    0.39
     diámetro
    0.39
     diamètre
    0.38
     largura
    0.38
     özelliği
    0.37
     veya
    0.37
     poput
    0.37
     tambahan
    0.36
    Activations Density 0.004%

    No Known Activations