© 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. 64626
    Prev
    Next
    INDEX
    Explanations

    legacy applications

    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
    녈
    0.45
    は見
    0.44
     semblables
    0.43
     задание
    0.43
    画像を
    0.42
     документ
    0.41
     けれど
    0.41
    <0xAA>
    0.41
     こう
    0.41
    訓練
    0.41
    POSITIVE LOGITS
     spring
    0.44
     Alternatively
    0.43
     Approximately
    0.43
     ২৯
    0.42
     Milan
    0.42
     requires
    0.42
     approximately
    0.42
     mach
    0.40
     April
    0.40
    fromString
    0.40
    Activations Density 0.030%

    No Known Activations