© 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. 217347
    Prev
    Next
    INDEX
    Explanations

    bible verses about stars

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

    if it

    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
     vulve
    0.53
    妲
    0.52
     искусство
    0.52
     वनस्पती
    0.52
     gamanam
    0.51
     असल्यास
    0.51
     かわ
    0.50
    nicheskij
    0.50
     bimodule
    0.49
    ୬
    0.49
    POSITIVE LOGITS
    -
    0.59
     is
    0.55
    z
    0.55
     they
    0.54
    .
    0.52
    Cal
    0.52
    y
    0.52
     The
    0.51
     Gary
    0.51
    tec
    0.51
    Activations Density 0.001%

    No Known Activations