© 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. 65271
    Prev
    Next
    INDEX
    Explanations

    pay in, work, pay in, clinical, hearts, talk, parliaments

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

    officially, constantly, brains

    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
    ру
    0.50
    ます
    0.50
    는
    0.46
    음
    0.46
    區域
    0.44
    導
    0.44
    )
    0.44
    ת
    0.44
    ]
    0.43
     プラ
    0.42
    POSITIVE LOGITS
     weren
    0.52
     बैठने
    0.49
     města
    0.49
    uddho
    0.48
     bior
    0.48
     hasilnya
    0.47
     शामिल
    0.46
    தியம்
    0.46
     হইলে
    0.45
    ன்கள்
    0.45
    Activations Density 0.000%

    No Known Activations