© 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. 25107
    Prev
    Next
    INDEX
    Explanations

    referring or discussing context

    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
     tùy
    0.41
    頹
    0.41
     szczę
    0.40
    ēc
    0.38
     besta
    0.38
     propuestas
    0.38
    ättre
    0.38
    efeu
    0.38
    Ę
    0.38
    愭
    0.37
    POSITIVE LOGITS
     referring
    0.51
     conversation
    0.46
    文中
    0.46
     discussing
    0.43
    で使用
    0.42
     refers
    0.41
     Referring
    0.41
    refer
    0.40
     conversación
    0.40
     refer
    0.40
    Activations Density 0.309%

    No Known Activations