© 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. 38728
    Prev
    Next
    INDEX
    Explanations

    contrasting information and lists

    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
     a
    0.47
    ﺝ
    0.45
     the
    0.41
    groupId
    0.41
     societies
    0.41
     exploded
    0.41
    σή
    0.41
    ته
    0.39
     gaseous
    0.39
     dumped
    0.39
    POSITIVE LOGITS
     बरकरार
    0.43
     खोजने
    0.43
    rategy
    0.42
    ให้บริการ
    0.42
     выполнять
    0.42
     क्रम
    0.42
    虺
    0.41
     керек
    0.40
    acariy
    0.39
     যেকোন
    0.39
    Activations Density 0.006%

    No Known Activations