© 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. 95817
    Prev
    Next
    INDEX
    Explanations

    software, indefinite duration, negative outcomes, strong emotions, pets, enjoyment

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

    break down / do you mean

    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
    0.66
    ↵↵↵
    0.59
    ↵↵
    0.58
    ↵
    0.49
     refreshed
    0.48
     using
    0.48
    ↵↵↵↵↵
    0.47
    ↵↵↵↵
    0.46
     indication
    0.46
     configuration
    0.45
    POSITIVE LOGITS
    ങ്ങളിലും
    0.50
     মানবতার
    0.50
    च्युअल
    0.49
     осозна
    0.49
    Donate
    0.49
    先天
    0.48
    సూ
    0.47
     நன்க
    0.47
    砊
    0.46
     विरासत
    0.46
    Activations Density 0.003%

    No Known Activations