© 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. 174819
    Prev
    Next
    INDEX
    Explanations

    able to refund or sustain

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

    cubes

    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
    P
    0.49
    柘
    0.47
    International
    0.47
    Soul
    0.47
     ампли
    0.46
    ЕТ
    0.46
    F
    0.45
    Survived
    0.45
    S
    0.45
    وبه
    0.44
    POSITIVE LOGITS
     นั้น
    0.50
     عبادت
    0.49
     loving
    0.48
     craindre
    0.48
     criança
    0.48
     fatorial
    0.44
     কর্তৃক
    0.44
     setCount
    0.43
    ase
    0.43
     enceinte
    0.43
    Activations Density 0.001%

    No Known Activations