© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 124052
    Prev
    Next
    INDEX
    Explanations

    introducing myself and joining

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

    joining and new beginnings

    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
    OSPHER
    0.47
    🗑
    0.43
     माझ्या
    0.43
     স্বয়ং
    0.41
     পরেও
    0.41
    在我
    0.41
     不要
    0.41
     ئەو
    0.40
    묽
    0.40
    মাস
    0.40
    POSITIVE LOGITS
     bergabung
    0.68
     joining
    0.58
     присоеди
    0.58
     join
    0.56
    joining
    0.54
     joined
    0.52
     joins
    0.52
     Joining
    0.52
     saludo
    0.50
     Join
    0.50
    Activations Density 0.072%

    No Known Activations