© 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. 14261
    Prev
    Next
    INDEX
    Explanations

    sharing and activities

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

    sharing knowledge and personal contributions

    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
    你
    0.59
    Ж
    0.58
    ，$
    0.55
    一阵
    0.54
    ፂ
    0.53
    斯的
    0.53
    一组
    0.53
    一批
    0.52
    Му
    0.50
    О
    0.50
    POSITIVE LOGITS
     condiv
    1.00
     berbagi
    0.96
     sharing
    0.95
     share
    0.95
     compartilhar
    0.92
     공유
    0.91
     Sharing
    0.89
     compartilh
    0.88
     conosco
    0.84
    分享
    0.82
    Activations Density 0.078%

    No Known Activations