© 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. 60879
    Prev
    Next
    INDEX
    Explanations

    educational excellence

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

    equations and scientific terms

    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
    菜单
    0.59
    运作
    0.55
    🍟
    0.52
    📄
    0.50
     podía
    0.50
    绁
    0.50
     αρκε
    0.50
    谈
    0.49
     podían
    0.49
     менедже
    0.49
    POSITIVE LOGITS
     myeloid
    0.51
     silicate
    0.48
    radiation
    0.47
     inscr
    0.46
     Burkina
    0.45
     harnessed
    0.44
    ulins
    0.44
     crater
    0.43
     brownish
    0.43
     gazing
    0.43
    Activations Density 0.000%

    No Known Activations