© 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. 23726
    Prev
    Next
    INDEX
    Explanations

    symbols before phrases

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

    relationship between actions and consequences

    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
     I
    0.54
     use
    0.54
    can
    0.54
     can
    0.53
    use
    0.53
    type
    0.53
    required
    0.50
     Use
    0.50
     S
    0.49
     $
    0.49
    POSITIVE LOGITS
     rumores
    0.55
     yaşanan
    0.52
     Öffentlichkeit
    0.50
     nieuws
    0.49
    öffentlich
    0.48
     noticias
    0.48
     финансо
    0.48
     estranged
    0.47
     affaires
    0.47
     estrange
    0.47
    Activations Density 0.002%

    No Known Activations