© 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. 86244
    Prev
    Next
    INDEX
    Explanations

    come back, testify after

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

    structuring lists, bullet points, or parenthetical explanations

    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
     rum
    0.51
     Rum
    0.50
    一
    0.47
    本
    0.45
     Groove
    0.44
    rum
    0.44
     lyrical
    0.44
     Chen
    0.43
     Cheng
    0.43
     Zeta
    0.43
    POSITIVE LOGITS
    ForSettings
    0.50
    vät
    0.48
     ivvu
    0.48
     hôtels
    0.47
    વાના
    0.47
    ႆ
    0.46
     рэгістрацыі
    0.46
     měli
    0.46
     bhavanti
    0.46
     działalności
    0.46
    Activations Density 0.000%

    No Known Activations