© 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. 44685
    Prev
    Next
    INDEX
    Explanations

    the fact that

    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
     confronto
    0.62
    ções
    0.59
    ٹ
    0.57
     godziny
    0.56
     võivad
    0.56
    دی
    0.55
    ۹
    0.54
    دى
    0.54
    દ્ધ
    0.54
     caractér
    0.54
    POSITIVE LOGITS
     ότι
    0.65
    ’
    0.64
    p
    0.59
    t
    0.59
     fact
    0.58
    被
    0.55
     bahwa
    0.54
    在于
    0.54
     myosin
    0.52
     rằng
    0.50
    Activations Density 0.020%

    No Known Activations