© 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. 161747
    Prev
    Next
    INDEX
    Explanations

    website security and data storage

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

    GDP, Mac, risk

    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
    焲
    0.54
     имају
    0.52
    prä
    0.51
     അവസ്ഥ
    0.50
    abhavena
    0.50
    міст
    0.49
    墮
    0.49
     אוי
    0.49
    біць
    0.49
    ჲ
    0.48
    POSITIVE LOGITS
     land
    0.56
     stress
    0.54
     T
    0.53
     risk
    0.53
     unsafe
    0.53
     press
    0.52
     harm
    0.51
     Som
    0.51
     hilo
    0.51
     beer
    0.51
    Activations Density 0.000%

    No Known Activations