© 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. 142062
    Prev
    Next
    INDEX
    Explanations

    shrinking again

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

    misconception stemming

    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
    ARGET
    0.46
     hausse
    0.43
     producer
    0.42
    ObjData
    0.41
     adultos
    0.41
    trading
    0.41
     actives
    0.41
    է
    0.41
     trading
    0.40
     fodder
    0.40
    POSITIVE LOGITS
     Nuestro
    0.57
     Bathroom
    0.50
     Layout
    0.49
     Kala
    0.47
     Tele
    0.47
     Abdullah
    0.46
     Poon
    0.45
    apayati
    0.44
     Nautical
    0.44
     Prayer
    0.44
    Activations Density 0.001%

    No Known Activations