© 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. 123775
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    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
     repressive
    0.48
    empty
    0.44
    form
    0.39
    lead
    0.39
     comprehension
    0.39
    ifiable
    0.39
    柯
    0.39
    cookbook
    0.39
    )
    0.38
     rue
    0.38
    POSITIVE LOGITS
     otáz
    0.51
    表達
    0.51
    珣
    0.47
     обозна
    0.46
    iąz
    0.45
     সাত
    0.44
     प्रश्
    0.44
    újo
    0.44
    摷
    0.44
    ؤال
    0.43
    Activations Density 0.005%

    No Known Activations