© 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. 84350
    Prev
    Next
    INDEX
    Explanations

    prize and opportunity

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

    wave-particle duality

    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
    ύτε
    0.46
    咬
    0.46
    }`
    0.45
    های
    0.44
    ẳng
    0.44
    ն
    0.44
     merely
    0.44
     leaned
    0.43
    我们要
    0.42
    谘
    0.42
    POSITIVE LOGITS
    pkins
    0.49
    рос
    0.44
    batas
    0.43
     peritone
    0.42
    ítható
    0.42
     poisons
    0.41
     popula
    0.41
    IOD
    0.41
     رحم
    0.41
    onos
    0.41
    Activations Density 0.001%

    No Known Activations