© 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. 31-GEMMASCOPE-2-RES-262K
    7. 203086
    Prev
    Next
    INDEX
    Explanations

    `overlay` or `Shape`

    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_31_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
     cias
    0.52
     tomar
    0.50
     passare
    0.46
     lancio
    0.46
    客
    0.46
     मैन
    0.45
     व्हाउचर
    0.45
     View
    0.45
    伀
    0.45
     trovare
    0.45
    POSITIVE LOGITS
    しの
    0.45
     angesch
    0.44
     حتی
    0.43
    PAL
    0.43
    ଆ
    0.42
    োর
    0.41
     affective
    0.41
     اهمیت
    0.40
    ardini
    0.39
    IP
    0.39
    Activations Density 0.000%

    No Known Activations