© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 6182
    Prev
    Next
    INDEX
    Explanations

    legal codes and social roles

    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
    ☯
    0.42
    ceans
    0.41
    sterne
    0.41
     ダイヤモンド
    0.41
    ideos
    0.40
     становятся
    0.40
    に関連
    0.39
     असतात
    0.39
     डाइऑक्साइड
    0.39
    responsive
    0.38
    POSITIVE LOGITS
    得知
    0.38
     dày
    0.38
    NotBlank
    0.38
     >>>
    0.36
     Lec
    0.36
     army
    0.35
     scaling
    0.35
     CEN
    0.35
     Renov
    0.35
     billed
    0.35
    Activations Density 0.008%

    No Known Activations