© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 13652
    Prev
    Next
    INDEX
    Explanations

    modal component or operation

    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_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
    antiates
    0.46
     undisputed
    0.46
    যজ্ঞ
    0.46
    რც
    0.44
     clearest
    0.41
    ளிர்
    0.41
     সংকোচন
    0.41
    Ỷ
    0.41
    涑
    0.40
     wearer
    0.39
    POSITIVE LOGITS
    ，
    0.46
    。
    0.45
    ╠
    0.43
     modalità
    0.43
    耍
    0.43
     fantástico
    0.42
     {
    0.42
     प्रतिबंधित
    0.41
    बलेट
    0.41
    Moder
    0.40
    Activations Density 0.001%

    No Known Activations