© 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. 57209
    Prev
    Next
    INDEX
    Explanations

    legal and grammatical structures

    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
    isPreview
    0.45
    ^)
    0.42
    uí
    0.42
    었고
    0.41
    khart
    0.40
    ámara
    0.39
    ^*
    0.39
    环
    0.38
    urangi
    0.38
    localObject
    0.37
    POSITIVE LOGITS
    TION
    0.50
     commandments
    0.45
     commandment
    0.45
     tasks
    0.44
    PTION
    0.42
     eens
    0.42
     alcoholic
    0.42
     Commandments
    0.41
     archery
    0.41
     அரசியல்
    0.40
    Activations Density 0.021%

    No Known Activations