© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 133596
    Prev
    Next
    INDEX
    Explanations

    copyright notices and preferred items

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

    identify patterns

    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
     señal
    0.60
     நிலையில்
    0.57
    btnInventory
    0.55
     сигнала
    0.54
    pickMenu
    0.52
     dừng
    0.51
    deployRoot
    0.51
     °,
    0.51
     思っ
    0.51
     nhớ
    0.50
    POSITIVE LOGITS
    uct
    0.50
     esteem
    0.49
    на
    0.47
    Type
    0.45
     mediums
    0.44
    ling
    0.44
    uction
    0.43
     intermediary
    0.42
    na
    0.42
     variations
    0.41
    Activations Density 0.000%

    No Known Activations