© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14494
    Prev
    Next
    INDEX
    Explanations

    type followed by of or colon

    np_acts-logits-general · gemini-2.5-flash-lite

    identifying type followed by separator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ی
    0.86
    י
    0.82
    ים
    0.80
    ת
    0.80
    ي
    0.79
    т
    0.76
    𝘴
    0.73
    </b>
    0.72
    ி
    0.70
    ের
    0.70
    POSITIVE LOGITS
    Type
    0.88
    Types
    0.84
    Typ
    0.76
    SubType
    0.74
    Valid
    0.73
     类型
    0.73
    TypeName
    0.70
    TypeList
    0.70
    GetType
    0.70
     getType
    0.70
    Activations Density 0.272%

    No Known Activations