© 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. 97195
    Prev
    Next
    INDEX
    Explanations

    PTSD and decreases

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

    air resistance, Latina, black cats

    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
    ớ
    0.60
    OTHER
    0.47
    SEPARATOR
    0.47
    ION
    0.44
    G
    0.44
     MERCHANT
    0.44
    ၊
    0.44
    UN
    0.43
    Echo
    0.42
    쵸
    0.42
    POSITIVE LOGITS
     decreased
    0.58
     decreases
    0.57
     decreasing
    0.56
     chronically
    0.55
     decrease
    0.50
    decreasing
    0.49
     sexually
    0.47
     prednis
    0.46
    decrease
    0.46
     comorbid
    0.45
    Activations Density 0.001%

    No Known Activations