© 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. 66037
    Prev
    Next
    INDEX
    Explanations

    properties and similar

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

    superlative adjectives

    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
    וו
    0.56
    uddin
    0.52
    confirmed
    0.50
    кмекер
    0.50
    entuan
    0.50
    ika
    0.49
    ván
    0.49
    😩
    0.49
    rauch
    0.48
    ungkap
    0.48
    POSITIVE LOGITS
     mov
    0.51
     lamina
    0.49
     прямо
    0.48
     voltages
    0.48
     MOSFET
    0.48
     motion
    0.48
     ALPHA
    0.48
     cables
    0.47
     nac
    0.47
     movimiento
    0.47
    Activations Density 0.002%

    No Known Activations