© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 156352
    Prev
    Next
    INDEX
    Explanations

    welcome you to buy

    np_acts-logits-general · gemini-2.5-flash-lite

    more about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }
    0.49
    ↵↵
    0.44
    פ
    0.43
     actual
    0.42
            
    0.40
    ning
    0.40
    <h2>
    0.39
     বলা
    0.39
     gallons
    0.39
    ný
    0.39
    POSITIVE LOGITS
    耳机
    0.54
    𝙾
    0.52
    मिस्ट्री
    0.51
     требований
    0.50
     metaphysics
    0.48
     განს
    0.47
    ЕР
    0.47
    出发
    0.47
    ophenyl
    0.47
     ब्रै
    0.47
    Activations Density 0.001%

    No Known Activations