© 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. 183701
    Prev
    Next
    INDEX
    Explanations

    objects and components

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

    often foundational or crucial

    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
     bangsa
    0.45
    <unused2127>
    0.42
     Hamiltonian
    0.41
    রণের
    0.40
    服务端
    0.39
     ګرځنده
    0.39
     fetched
    0.39
     hoàng
    0.39
    ましたが
    0.39
     فونبټ
    0.39
    POSITIVE LOGITS
    UD
    0.53
    AD
    0.49
    UH
    0.49
     вижу
    0.49
    мой
    0.47
    1
    0.46
    ny
    0.46
    Customers
    0.46
     empate
    0.46
    PROBLEM
    0.46
    Activations Density 0.002%

    No Known Activations