© 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. 173633
    Prev
    Next
    INDEX
    Explanations

    sales department

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

    mathematical operations and outcomes

    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
    0
    0.55
     blieb
    0.50
     liten
    0.49
     특징
    0.49
    )、
    0.48
    )，
    0.46
     applicable
    0.46
    適合
    0.45
     用
    0.45
     feature
    0.44
    POSITIVE LOGITS
     وزير
    0.56
     Atlético
    0.54
     Gareth
    0.53
     برطانیہ
    0.53
    اديم
    0.52
     Biden
    0.50
    реа
    0.49
     Swansea
    0.49
     Tottenham
    0.49
     UEFA
    0.48
    Activations Density 0.001%

    No Known Activations