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-3-12B-IT
    3. 24-GEMMASCOPE-2-RES-16K
    4. 9917
    Prev
    Next
    INDEX
    Explanations

    Dockerfile examples, script files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_width_16k_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
     Воло
    0.76
     objectively
    0.76
     Visual
    0.74
     Atomic
    0.74
     professionally
    0.74
    랗
    0.73
     Achieving
    0.72
     अर्थात
    0.71
     Journalism
    0.71
     Rudd
    0.70
    POSITIVE LOGITS
    gek
    0.76
     подроб
    0.75
     taea
    0.75
    }$}
    0.74
    పె
    0.74
     зависи
    0.72
    tuk
    0.72
    స్
    0.72
     зависимости
    0.72
     vidi
    0.72
    Activations Density 0.002%

    No Known Activations