© 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. 26322
    Prev
    Next
    INDEX
    Explanations

    exploring RF technology

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

    The power of X / X of Y

    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
     Feast
    0.54
    🥳
    0.44
     unleashing
    0.41
     undoubt
    0.41
     unleashed
    0.41
     Wanna
    0.41
     feast
    0.41
     Chick
    0.40
     ‘
    0.40
     flawlessly
    0.39
    POSITIVE LOGITS
    數學
    0.54
     derivations
    0.47
     derivation
    0.46
     математи
    0.46
     تربيع
    0.45
     matemáticas
    0.45
     leichte
    0.43
     bảy
    0.43
     solubilities
    0.42
     deleting
    0.42
    Activations Density 0.000%

    No Known Activations