© 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. 39655
    Prev
    Next
    INDEX
    Explanations

    used with units

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

    describing specific roles or systems

    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
     abc
    0.51
     peso
    0.50
     delighted
    0.50
     य
    0.49
     pesa
    0.49
     bili
    0.49
     od
    0.48
     terrific
    0.47
     bollywood
    0.47
     awesome
    0.47
    POSITIVE LOGITS
    Used
    0.55
     Used
    0.52
     Designated
    0.50
     Designation
    0.49
    ﭥ
    0.48
    Needed
    0.47
     Modular
    0.47
    Completed
    0.46
    用於
    0.45
    Understanding
    0.45
    Activations Density 0.001%

    No Known Activations