© 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-262K
    7. 18202
    Prev
    Next
    INDEX
    Explanations

    linking verb followed by descriptor

    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_262k_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
    '
    0.45
     operadores
    0.40
    silhouette
    0.39
    म्ह
    0.39
    者的
    0.38
    మీ
    0.38
    を食べ
    0.38
     destinés
    0.37
    λει
    0.37
    ’
    0.37
    POSITIVE LOGITS
     tiež
    0.51
     причем
    0.45
    ječ
    0.41
    ণ্ড
    0.39
     natomiast
    0.39
     Qd
    0.38
     sane
    0.38
     cryptic
    0.38
    倶
    0.38
    烦
    0.38
    Activations Density 0.048%

    No Known Activations