© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13408
    Prev
    Next
    INDEX
    Explanations

    time ranges and numbers

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

    scheduled times and activities

    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_16k_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
     unwarrant
    0.39
    ՞
    0.39
     dishonest
    0.39
     incessant
    0.38
     leagues
    0.37
    LVANIA
    0.37
    쑤
    0.37
    팍
    0.35
     frantic
    0.35
    nonsense
    0.35
    POSITIVE LOGITS
    ته
    0.42
     Habitat
    0.40
     Grâce
    0.37
     One
    0.37
    可能是
    0.37
    Gary
    0.37
     Troy
    0.36
    修士
    0.36
     Gorge
    0.36
     Gary
    0.35
    Activations Density 0.074%

    No Known Activations