© 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. 88835
    Prev
    Next
    INDEX
    Explanations

    social connections or collaboration

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

    server-side rendering

    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
     سین
    0.46
     доступ
    0.44
     แ
    0.44
     서
    0.43
     جت
    0.42
     Fees
    0.42
     С
    0.42
     OR
    0.42
     ۱
    0.42
    ]
    0.42
    POSITIVE LOGITS
    aqueous
    0.46
    CTOGRAM
    0.40
    AndroidManifest
    0.40
    FolderPath
    0.40
    %>%
    0.39
    ichtig
    0.39
    tmpobj
    0.39
    Owin
    0.38
    ষ্কৃত
    0.38
     thofe
    0.38
    Activations Density 0.000%

    No Known Activations