© 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. 53-GEMMASCOPE-2-RES-262K
    7. 167133
    Prev
    Next
    INDEX
    Explanations

    listing items and descriptions

    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_53_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
    Extern
    0.37
     audit
    0.37
     sna
    0.37
     hive
    0.36
     Extern
    0.36
     Boyce
    0.36
     Brasil
    0.36
    뢰
    0.35
     Hive
    0.35
     wsp
    0.35
    POSITIVE LOGITS
    TOP
    0.41
    neider
    0.40
     truckers
    0.39
     dihydro
    0.39
    قر
    0.39
    Continued
    0.38
    ப்பான்
    0.38
    할
    0.38
     محفوظ
    0.38
    ompact
    0.38
    Activations Density 0.005%

    No Known Activations