© 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. 184802
    Prev
    Next
    INDEX
    Explanations

    starting to include

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

    dramatic landscape and risks

    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
     unchanged
    0.51
     kuu
    0.50
     unim
    0.49
     খ্র
    0.49
     ühe
    0.48
     convenient
    0.48
     suerte
    0.47
    ඌ
    0.46
     veine
    0.46
     indien
    0.46
    POSITIVE LOGITS
    開幕
    0.44
     ومد
    0.43
    拿
    0.43
    培
    0.42
    ler
    0.42
     ላ
    0.41
    ODB
    0.41
    Clos
    0.41
    oso
    0.41
    adas
    0.40
    Activations Density 0.001%

    No Known Activations