© 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. 28469
    Prev
    Next
    INDEX
    Explanations

    specific feelings and states

    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
     പിന്നീട്
    0.49
    促進
    0.46
    蘿
    0.44
     তথাপি
    0.44
    лід
    0.44
     റ
    0.42
     fomentar
    0.41
    Ŕ
    0.41
    ヮ
    0.41
     дальней
    0.40
    POSITIVE LOGITS
     anyone
    0.40
     Cubs
    0.39
     alebo
    0.39
     või
    0.37
    所有人
    0.37
     anybody
    0.37
    şa
    0.37
     शकत
    0.36
     Anyone
    0.36
     Lieutenant
    0.35
    Activations Density 0.012%

    No Known Activations