© 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. 16-GEMMASCOPE-2-RES-262K
    7. 6732
    Prev
    Next
    INDEX
    Explanations

    providing resources

    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
    সি
    0.43
    {
    0.42
    <0x91>
    0.42
    nên
    0.41
    <0x93>
    0.40
    ाई
    0.38
    <
    0.37
    ﺯ
    0.37
     than
    0.36
    ია
    0.36
    POSITIVE LOGITS
     educa
    0.54
     கல்வி
    0.52
     audiovis
    0.50
    <unused736>
    0.50
     Aztecs
    0.49
    wne
    0.48
    <unused1087>
    0.48
    <unused641>
    0.48
     avere
    0.48
     AcOH
    0.48
    Activations Density 0.023%

    No Known Activations