© 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. 40-GEMMASCOPE-2-RES-262K
    7. 14414
    Prev
    Next
    INDEX
    Explanations

    knowledge and reasoning

    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_40_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
    하였
    0.43
    යට
    0.35
    نيا
    0.34
    жают
    0.34
    禳
    0.34
    Essay
    0.32
    だったので
    0.31
    했으며
    0.31
     Gospels
    0.31
    ]，
    0.31
    POSITIVE LOGITS
     aware
    0.41
     know
    0.37
     unaware
    0.37
     sure
    0.37
     unsure
    0.37
     знаете
    0.36
     Know
    0.35
     unclear
    0.35
    您可以
    0.35
     remember
    0.35
    Activations Density 0.000%

    No Known Activations