© 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. 194100
    Prev
    Next
    INDEX
    Explanations

    saltpans and patch view

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

    strategies for protection and research

    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
    )
    0.53
     отри
    0.49
     श्रद्धा
    0.48
    تقاوى
    0.48
    dR
    0.47
     również
    0.47
    ]]))
    0.46
     קי
    0.45
    ༽
    0.45
     dvar
    0.45
    POSITIVE LOGITS
    疾
    0.47
    的企业
    0.45
    的公司
    0.44
     Sill
    0.44
    يرات
    0.43
    叫
    0.43
    識
    0.42
    明
    0.42
    傷
    0.41
     Maintain
    0.41
    Activations Density 0.000%

    No Known Activations