© 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. 7645
    Prev
    Next
    INDEX
    Explanations

    afterward

    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
     skall
    0.48
     haem
    0.40
    GALAD
    0.40
    ڎ
    0.39
     accomod
    0.38
    kken
    0.38
     diantaranya
    0.37
    Ｘ
    0.37
     dimana
    0.37
    쉘
    0.37
    POSITIVE LOGITS
     به‌
    0.44
     Afterward
    0.42
     महत्त्वपूर्ण
    0.41
    —
    0.41
    <0xC2>
    0.40
     그다음에
    0.40
    –
    0.39
     به‌عنوان
    0.38
     afterward
    0.38
    â
    0.38
    Activations Density 0.030%

    No Known Activations