© 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. 101822
    Prev
    Next
    INDEX
    Explanations

    anonymous and anonymity

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

    anonymous / anonymity

    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
     mapas
    0.41
    研
    0.41
    TGFuZ
    0.40
    িস
    0.40
     تجاوز
    0.40
    ibouti
    0.40
    ResBuffer
    0.39
     స్వా
    0.39
     读取
    0.39
    ק
    0.38
    POSITIVE LOGITS
     anonymous
    1.52
     anonymity
    1.45
     Anonymous
    1.45
     anonymously
    1.43
    anonymous
    1.34
    匿名
    1.32
     anon
    1.30
     anonym
    1.29
    Anonymous
    1.28
     Anon
    1.23
    Activations Density 0.150%

    No Known Activations