© 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. 190737
    Prev
    Next
    INDEX
    Explanations

    tax free, ways to, source and

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

    describes subsequent components or outcomes

    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
     بين
    0.50
    则是
    0.46
    نة
    0.44
     competición
    0.44
    ır
    0.44
    之一
    0.44
    则
    0.43
    ٦
    0.43
     المك
    0.42
     position
    0.42
    POSITIVE LOGITS
    œurs
    0.49
    हेलो
    0.48
    গতির
    0.47
    🎁
    0.47
    🐶
    0.46
     brushed
    0.46
    🏡
    0.45
     savor
    0.45
    夫人
    0.45
    আমাদের
    0.44
    Activations Density 0.000%

    No Known Activations