© 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-65K
    7. 4836
    Prev
    Next
    INDEX
    Explanations

    being or states following nouns

    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
     these
    0.55
     this
    0.50
     نیست
    0.50
     với
    0.47
     hasn
    0.46
    ，
    0.46
     этих
    0.46
     will
    0.44
    ،
    0.44
     هذه
    0.44
    POSITIVE LOGITS
     being
    0.61
     emphasis
    0.59
    being
    0.56
     sendo
    0.56
     implications
    0.56
     siendo
    0.52
     énfasis
    0.50
    emphasis
    0.48
     podendo
    0.48
     Emphasis
    0.46
    Activations Density 0.222%

    No Known Activations