© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 16821
    Prev
    Next
    INDEX
    Explanations

    members or beneficiaries

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

    member or members

    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_53_width_65k_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
    DataType
    0.40
    🔁
    0.38
     consequat
    0.35
    dataType
    0.34
    żliw
    0.33
    ር
    0.33
     mosa
    0.33
     epithelium
    0.32
     laten
    0.32
    ̯
    0.32
    POSITIVE LOGITS
     member
    4.63
     members
    4.56
    members
    4.41
    成员
    4.41
    member
    4.31
    Members
    4.28
     Members
    4.25
    メンバー
    4.25
     membres
    4.19
     miembro
    4.19
    Activations Density 0.855%

    No Known Activations