© 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-262K
    4. 100076
    Prev
    Next
    INDEX
    Explanations

    immediate aftermath or initial features

    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
     Liability
    0.45
    跄
    0.44
     የተቀ
    0.43
     다시
    0.41
    abilirsiniz
    0.41
     WrestleMania
    0.41
    进制
    0.41
     सिद्धांत
    0.40
    语气
    0.40
     tekrar
    0.40
    POSITIVE LOGITS
    ม
    0.46
    Replace
    0.44
    EG
    0.44
    Either
    0.44
    或
    0.43
    Eg
    0.43
     پیغم
    0.43
    หรือ
    0.42
    Lots
    0.42
    Buffalo
    0.41
    Activations Density 0.012%

    No Known Activations