© 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. 58588
    Prev
    Next
    INDEX
    Explanations

    knowledge and measurements

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

    sequence flawlessly

    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
    nak
    0.41
     multiplicities
    0.40
    Nb
    0.40
     reunions
    0.39
     reunion
    0.38
    碳
    0.38
    針
    0.37
    :]
    0.37
     తమి
    0.37
     felonies
    0.37
    POSITIVE LOGITS
    不说
    0.51
     یہ
    0.50
    ùa
    0.48
    ación
    0.46
     åt
    0.46
     각각
    0.45
    諌
    0.45
    夆
    0.45
    Ⲁ
    0.45
     특히
    0.45
    Activations Density 0.000%

    No Known Activations