© 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. 148139
    Prev
    Next
    INDEX
    Explanations

    quantification and duration

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

    Moderate Complexity

    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
    込め
    0.46
    籬
    0.44
    룰
    0.42
    reliance
    0.42
     മാത്രം
    0.41
    子ども
    0.41
    Ა
    0.41
    an
    0.40
    込み
    0.40
    টির
    0.40
    POSITIVE LOGITS
     nogle
    0.47
     terminate
    0.43
     lask
    0.42
     sets
    0.41
     mehrere
    0.41
     noen
    0.41
     flere
    0.40
     hukum
    0.40
     ř
    0.40
     някои
    0.40
    Activations Density 0.001%

    No Known Activations