Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 1932
    Prev
    Next
    INDEX
    Explanations

    event or discovery following subject

    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
    ➸
    0.43
    璿
    0.43
     گفته
    0.42
    㑹
    0.41
     সাম্রাজ
    0.41
     ชอบ
    0.41
    ುವುದು
    0.41
    }({\
    0.40
     வாழ
    0.40
    मूल
    0.40
    POSITIVE LOGITS
     overhear
    1.07
    发现
    1.04
     overheard
    0.99
     noticed
    0.98
     обнаружи
    0.96
    發現
    0.96
     accidentally
    0.93
     discover
    0.88
     discovered
    0.88
     hear
    0.87
    Activations Density 0.008%

    No Known Activations