© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 50490
    Prev
    Next
    INDEX
    Explanations

    metaphorical, different, deeper relationships

    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
    協議
    0.55
    স
    0.53
    ,",
    0.46
     endothelial
    0.46
     mattresses
    0.46
     pods
    0.45
     personas
    0.45
     dwellers
    0.45
     booties
    0.45
     heterozyg
    0.44
    POSITIVE LOGITS
     freely
    0.41
    활
    0.40
     expands
    0.40
    発展
    0.40
     Zeal
    0.40
     നി
    0.39
     prolific
    0.39
     corroborate
    0.39
    anton
    0.39
     විස
    0.39
    Activations Density 0.008%

    No Known Activations