© 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. 114574
    Prev
    Next
    INDEX
    Explanations

    Water Ionizers make alkaline

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

    technical terms and examples

    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
    áciu
    0.44
    burg
    0.42
    <0x80>
    0.42
    國
    0.41
    面前
    0.40
    _,
    0.39
    illy
    0.39
    કડ
    0.39
    ﺿ
    0.39
    iberg
    0.38
    POSITIVE LOGITS
     घड़ी
    0.53
     शिलाजीत
    0.51
     ذہ
    0.51
     भौगोलिक
    0.50
    އ
    0.50
     была
    0.50
     inferences
    0.50
     normalcy
    0.50
     hindsight
    0.50
     आरओ
    0.50
    Activations Density 0.000%

    No Known Activations