© 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. 16-GEMMASCOPE-2-RES-262K
    4. 11570
    Prev
    Next
    INDEX
    Explanations

    past events

    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_16_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
     to
    0.44
    یس
    0.44
    τή
    0.43
    を見
    0.40
     άλλα
    0.40
    د
    0.39
     други
    0.38
     feeders
    0.38
     entrant
    0.38
    しっかり
    0.37
    POSITIVE LOGITS
    و
    0.51
    <0x0D>
    0.48
    l
    0.47
    2
    0.44
    res
    0.43
    Col
    0.42
     ছোট্ট
    0.41
     fiery
    0.41
     americana
    0.40
    ल
    0.40
    Activations Density 0.010%

    No Known Activations