© 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-65K
    7. 5390
    Prev
    Next
    INDEX
    Explanations

    how to convert or install

    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_65k_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
    datei
    0.38
    MenuStyle
    0.38
    棧
    0.38
    FName
    0.37
    údo
    0.37
    webBrowser
    0.37
    ındadır
    0.36
    offsets
    0.36
    㖷
    0.36
    StartPosition
    0.35
    POSITIVE LOGITS
     Microsoft
    0.37
     Monica
    0.37
     Alexis
    0.36
     Daniel
    0.35
     approaches
    0.35
     PD
    0.34
     SDK
    0.34
     OpenAI
    0.34
     Gary
    0.33
     leverage
    0.33
    Activations Density 0.168%

    No Known Activations