© 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. 29695
    Prev
    Next
    INDEX
    Explanations

    content creation and connection

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

    creating or producing content

    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
    োনা
    0.49
    নে
    0.48
    ン
    0.46
    வில
    0.43
    ົງ
    0.43
    ING
    0.43
     accusations
    0.42
    誣
    0.42
    ᅩ
    0.42
    isations
    0.41
    POSITIVE LOGITS
     menyediakan
    0.56
     básicamente
    0.53
     creates
    0.52
     menemukan
    0.50
     fornece
    0.49
     poskyt
    0.49
     tempat
    0.49
     basicamente
    0.49
     menghasilkan
    0.48
     Tempat
    0.48
    Activations Density 0.000%

    No Known Activations