© 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. 197474
    Prev
    Next
    INDEX
    Explanations

    online casinos and businesses

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

    code structures and logic

    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
     edildi
    0.53
     نی
    0.51
    時間は
    0.51
    逝
    0.51
     successivo
    0.49
     toekom
    0.47
     同じ
    0.47
    笄
    0.47
     skole
    0.46
     peristiwa
    0.46
    POSITIVE LOGITS
    with
    0.55
     with
    0.52
    JH
    0.49
    )
    0.49
    ),
    0.46
     With
    0.45
     online
    0.45
     resellers
    0.45
     Online
    0.44
    angaroo
    0.43
    Activations Density 0.000%

    No Known Activations