© 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. 112220
    Prev
    Next
    INDEX
    Explanations

    contrasting statements

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

    technical phrases and terms

    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
    ட்ட
    0.47
    duh
    0.45
    dalam
    0.43
    sum
    0.42
    ઃ
    0.42
     Increase
    0.41
    Increase
    0.41
    uruh
    0.39
    Bring
    0.39
    X
    0.38
    POSITIVE LOGITS
     বক্স
    0.45
    口碑
    0.45
     ఆలో
    0.44
    是没有
    0.43
     실패
    0.43
     моги
    0.43
     situations
    0.42
     hostel
    0.42
     ситуа
    0.41
     situazioni
    0.41
    Activations Density 0.005%

    No Known Activations