© 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. 162168
    Prev
    Next
    INDEX
    Explanations

    to work closely/together

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

    give a picture

    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
    ă
    0.48
    li
    0.46
     sentimental
    0.43
    ë
    0.43
    textAllCaps
    0.42
     casco
    0.42
     singly
    0.41
     stehen
    0.41
     beton
    0.41
     bestimm
    0.41
    POSITIVE LOGITS
    喑
    0.45
     inoculum
    0.45
    ግብ
    0.44
     सकें
    0.44
    問い合わせ
    0.43
    找出
    0.43
     Orphans
    0.43
    𒄩
    0.42
     读取
    0.42
    者的
    0.42
    Activations Density 0.000%

    No Known Activations