© 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. 33687
    Prev
    Next
    INDEX
    Explanations

    individual schools

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

    need for excitement

    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
    pra
    0.54
    の色
    0.46
    س
    0.45
    趾
    0.45
    medio
    0.45
    linkLabel
    0.45
     प्रक्रियाओं
    0.44
    onc
    0.44
     Beneficial
    0.44
    ema
    0.44
    POSITIVE LOGITS
    옷
    0.51
     eenvoudig
    0.45
    一丝
    0.44
     transact
    0.43
     defaultstate
    0.42
     legitimately
    0.42
     đừng
    0.42
     passaggio
    0.42
     deviate
    0.41
     uređ
    0.41
    Activations Density 0.001%

    No Known Activations