© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 168527
    Prev
    Next
    INDEX
    Explanations

    visual distortion or aspect ratio

    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
    秾
    0.52
    isu
    0.48
    updateConfirm
    0.48
     ಉತ್ತರ
    0.47
    煕
    0.46
    કિસ્
    0.46
    िरिक्स
    0.46
    JKLMNOP
    0.45
     unkind
    0.45
    ⇰
    0.45
    POSITIVE LOGITS
    s
    0.80
    h
    0.53
    t
    0.51
     journey
    0.48
     exchanges
    0.47
     gre
    0.47
    g
    0.46
     adventure
    0.46
    |
    0.45
     preview
    0.45
    Activations Density 0.002%

    No Known Activations