© 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. 15400
    Prev
    Next
    INDEX
    Explanations

    names and roles

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

    describing things in lists

    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
    Todas
    0.51
    LowerCase
    0.50
     ニ
    0.49
    isierte
    0.48
    ų
    0.48
    Ă
    0.48
     servidores
    0.47
     lowercase
    0.46
    ພວກເຮ
    0.46
     complesso
    0.46
    POSITIVE LOGITS
    预防
    0.46
     أقل
    0.43
    嗓
    0.42
    Trab
    0.41
    电话
    0.40
    讨论
    0.40
    松
    0.40
     Revis
    0.39
     सुनें
    0.39
    보는
    0.39
    Activations Density 0.000%

    No Known Activations