© 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. 206698
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    prices can vary

    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
     malignancies
    0.46
     gaps
    0.43
     weaknesses
    0.42
     ቦ
    0.42
     repulsion
    0.42
     poised
    0.42
     relish
    0.41
     gunfire
    0.41
     sunlight
    0.40
     prol
    0.40
    POSITIVE LOGITS
    asem
    0.43
    买
    0.42
    uales
    0.42
    ່າຍ
    0.41
    servicio
    0.41
    受信
    0.40
    アイテム
    0.40
    欲
    0.40
    興味
    0.40
    栍
    0.40
    Activations Density 0.001%

    No Known Activations