© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 88073
    Prev
    Next
    INDEX
    Explanations

    not all / not every

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_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
    ad
    0.86
    fromParams
    0.71
    țit
    0.70
    陘
    0.70
     ډول
    0.69
     فی
    0.68
    avacan
    0.68
    incoming
    0.66
    ind
    0.66
     dipped
    0.66
    POSITIVE LOGITS
    *
    0.88
    ن
    0.87
    ]
    0.78
    是
    0.76
    时
    0.75
    :
    0.75
    )
    0.71
    งาน
    0.67
    س
    0.67
    会
    0.66
    Activations Density 0.008%

    No Known Activations