© 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. 89502
    Prev
    Next
    INDEX
    Explanations

    blow followed by off, out, or away

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

    blowing and its 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
     WIRE
    0.58
     trastorno
    0.54
    িক
    0.53
     AUSTRAL
    0.50
    typeparam
    0.50
     〢
    0.50
    ್ಟ
    0.50
     (^{
    0.49
     SYM
    0.48
     Tutak
    0.48
    POSITIVE LOGITS
    吹
    1.02
    Blow
    0.86
     blowing
    0.85
     Blow
    0.84
     blow
    0.84
    blow
    0.83
     Blowing
    0.80
     blown
    0.79
     blew
    0.78
    blowing
    0.77
    Activations Density 0.018%

    No Known Activations