© 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. 29859
    Prev
    Next
    INDEX
    Explanations

    finding common word pairs

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

    trained, entrenado, acquises, sở hữu

    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
     ইলেক্ট্রোড
    0.38
     tématu
    0.37
     lLoginID
    0.37
     فائلوں
    0.37
    鿢
    0.35
     କରି
    0.35
     它
    0.34
     vettore
    0.33
    ِمض
    0.33
     fünf
    0.33
    POSITIVE LOGITS
    -
    0.36
     E
    0.36
    7
    0.35
    1
    0.34
    А
    0.34
    9
    0.33
     A
    0.32
    3
    0.32
    /
    0.32
     B
    0.32
    Activations Density 0.020%

    No Known Activations