© 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. 15852
    Prev
    Next
    INDEX
    Explanations

    essential that

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

    discontinued or managed

    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
    当时
    0.50
     않았다
    0.43
    当时的
    0.43
    攻擊
    0.43
    當時
    0.42
     ní
    0.42
    那时候
    0.41
    小
    0.40
    Attack
    0.39
    那时
    0.39
    POSITIVE LOGITS
     ২০২৩
    0.54
     allows
    0.51
     ২০২২
    0.50
     intends
    0.49
     underscores
    0.49
     promotes
    0.48
     requires
    0.47
     allowing
    0.47
    শিষ্ট
    0.47
     necessitates
    0.47
    Activations Density 0.000%

    No Known Activations