© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 133336
    Prev
    Next
    INDEX
    Explanations

    Groundwater Recharge

    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_40_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
    "。
    0.45
    Gob
    0.40
    夜
    0.39
    ക്തി
    0.39
    oretical
    0.38
     ጥቅ
    0.38
     ක්ර
    0.36
    सेप्ट
    0.36
    OLYBDENUM
    0.36
    𒊒
    0.36
    POSITIVE LOGITS
     women
    0.47
     Fourteen
    0.45
     Existence
    0.44
     habitants
    0.44
     queen
    0.44
     lvl
    0.43
     여자
    0.41
    여자
    0.41
     Look
    0.39
     ladies
    0.39
    Activations Density 0.000%

    No Known Activations