© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 96923
    Prev
    Next
    INDEX
    Explanations

    listed items or information

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

    high: symbols and guided success

    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
     করেছিলাম
    0.50
    Arrays
    0.48
    কিন্তু
    0.47
     alakalı
    0.45
     जाँच
    0.44
    ὤ
    0.43
     перева
    0.42
    跗
    0.42
     গুল
    0.41
    বসাই
    0.41
    POSITIVE LOGITS
    udor
    0.47
     incandescent
    0.46
     espera
    0.45
     lector
    0.44
     rhenium
    0.43
     reliant
    0.42
     tent
    0.42
     landslide
    0.42
     derm
    0.42
    ormous
    0.42
    Activations Density 0.002%

    No Known Activations