© 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. 111764
    Prev
    Next
    INDEX
    Explanations

    localized disruptions

    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
     Yankees
    0.39
    Malaysia
    0.38
     naman
    0.38
     latent
    0.36
     mildly
    0.36
    ਲਾਂ
    0.35
    Ϩ
    0.35
     Хабаровского
    0.34
    newData
    0.34
    poses
    0.34
    POSITIVE LOGITS
     …
    0.44
    …
    0.42
    ουν
    0.40
    …”
    0.40
    “…
    0.39
    ,}$
    0.38
     accordion
    0.38
    暴力
    0.38
    ூக
    0.37
    }...
    0.37
    Activations Density 0.002%

    No Known Activations