© 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. 78270
    Prev
    Next
    INDEX
    Explanations

    location or status updates

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

    scientific research and analysis

    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
    してお
    0.54
    にお
    0.48
    💧
    0.47
    '].
    0.46
    、
    0.46
    】
    0.46
    }'
    0.46
    原理
    0.45
     przede
    0.45
     rohk
    0.45
    POSITIVE LOGITS
    than
    0.49
    lar
    0.47
     वैकल्पिक
    0.46
     distortion
    0.45
    linearity
    0.45
     reflectivity
    0.44
     جرم
    0.44
    distortion
    0.44
     फ्री
    0.43
     बॅ
    0.43
    Activations Density 0.001%

    No Known Activations