© 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. 202519
    Prev
    Next
    INDEX
    Explanations

    forgiven sinner

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

    medical knowledge, patient history

    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
    ❂
    0.47
    I
    0.47
    htonl
    0.46
    hookrightarrow
    0.45
     Gefahr
    0.44
    vartheta
    0.44
    它們
    0.44
     particularmente
    0.43
     பெரும்பாலும்
    0.43
    ಎ
    0.43
    POSITIVE LOGITS
     songwriter
    0.58
    ார்
    0.51
     songwriting
    0.51
     songwriters
    0.46
     রেখে
    0.44
     legitim
    0.43
     Properties
    0.42
    ীল
    0.42
     denim
    0.41
     arranger
    0.41
    Activations Density 0.001%

    No Known Activations