© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 4871
    Prev
    Next
    INDEX
    Explanations

    bolding and formatting symbols

    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
    াঃ
    0.44
     planter
    0.41
    妝
    0.41
    才會
    0.40
    ্ধু
    0.40
    刖
    0.39
    鲵
    0.39
    チュラル
    0.39
    থায়
    0.38
     pollin
    0.38
    POSITIVE LOGITS
    5
    0.48
    ```
    0.44
    6
    0.44
     მაგრამ
    0.42
    }
    0.42
    {
    0.41
    https
    0.41
    note
    0.41
     Democrat
    0.41
    |
    0.41
    Activations Density 0.058%

    No Known Activations