© 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. 67795
    Prev
    Next
    INDEX
    Explanations

    motherboards

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

    freedom to run

    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
     首先
    0.50
     میری
    0.47
     एडवांस
    0.46
     线
    0.46
    <unused1049>
    0.46
     پوست
    0.46
     개념
    0.46
     不需要
    0.46
     εν
    0.46
    이라고
    0.46
    POSITIVE LOGITS
    :
    0.55
    )
    0.54
    ear
    0.52
    ni
    0.52
    li
    0.50
    だけでも
    0.49
    ä
    0.48
    elt
    0.48
    ]
    0.48
    j
    0.46
    Activations Density 0.000%

    No Known Activations