© 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. 203944
    Prev
    Next
    INDEX
    Explanations

    forming word pairs

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

    system isolates tries

    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
    慶
    0.54
    কট
    0.53
    当初
    0.51
    Instantiation
    0.50
    łu
    0.49
    ৌশ
    0.48
     اہ
    0.48
    പര
    0.48
    Initialization
    0.48
    ंग्रेस
    0.47
    POSITIVE LOGITS
     dissemin
    0.43
    <span>
    0.42
     d
    0.41
    隔
    0.41
     extrémités
    0.41
     Phyll
    0.41
    :
    0.41
     absorbs
    0.40
     glycerol
    0.40
     transformação
    0.40
    Activations Density 0.000%

    No Known Activations