© 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. 158965
    Prev
    Next
    INDEX
    Explanations

    drug abuse, concerns everyone

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

    differentiable computer, deals, evolves, inflicting pain

    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
     ㅛ
    0.50
     (°
    0.47
     insuficiente
    0.45
    要把
    0.44
    Შ
    0.44
     fetchData
    0.43
    绑
    0.43
    裄
    0.42
     すぎ
    0.42
    合金
    0.41
    POSITIVE LOGITS
    Usually
    0.49
     qual
    0.47
    Moved
    0.46
    EME
    0.46
     privat
    0.42
    IME
    0.42
    创业
    0.41
    deme
    0.41
     Thacker
    0.41
    Control
    0.41
    Activations Density 0.002%

    No Known Activations