© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 43260
    Prev
    Next
    INDEX
    Explanations

    various, some, each

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     că
    0.69
    otus
    0.69
    ো
    0.68
    區域
    0.66
    環境
    0.66
     втори
    0.65
    цата
    0.64
    我可以
    0.64
    🌷
    0.64
    經濟
    0.63
    POSITIVE LOGITS
    ]'
    0.82
     dhinak
    0.82
     vibhav
    0.81
    ्स
    0.78
    Thy
    0.77
    ];
    0.76
    রত্ব
    0.76
    Kabhi
    0.76
    larım
    0.75
     danam
    0.75
    Activations Density 0.000%

    No Known Activations