© 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. 112956
    Prev
    Next
    INDEX
    Explanations

    alpha and beta prefixes

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

    alpha and beta parameters

    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
    t
    0.81
    पी
    0.59
    nson
    0.58
    ONG
    0.58
    ine
    0.55
    י
    0.55
    ją
    0.55
    k
    0.54
    ंद
    0.53
    ו
    0.52
    POSITIVE LOGITS
     alpha
    0.98
     beta
    0.93
    alpha
    0.90
     Alpha
    0.88
    Alpha
    0.84
    ALPHA
    0.83
     Beta
    0.79
    Beta
    0.77
     alphas
    0.77
     ALPHA
    0.76
    Activations Density 0.194%

    No Known Activations