© 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. 256
    Prev
    Next
    INDEX
    Explanations

    type, request, or app settings

    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
    Methylsulfanyl
    0.46
    <unused51>
    0.42
    waterslide
    0.41
     मठ
    0.41
     Bisby
    0.41
    ˆ
    0.41
    <unused37>
    0.40
    maxcdn
    0.40
    fqsen
    0.39
    
    0.39
    POSITIVE LOGITS
    7
    0.46
    Type
    0.37
    TYPE
    0.36
    type
    0.36
    settings
    0.36
    aben
    0.36
    enc
    0.35
    app
    0.35
     term
    0.34
     bas
    0.34
    Activations Density 0.003%

    No Known Activations