© 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. 41129
    Prev
    Next
    INDEX
    Explanations

    Anchorblock Technology

    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
    _
    0.57
     संगठनों
    0.49
    很多
    0.49
    等你
    0.49
     Argentina
    0.49
    на
    0.48
    ja
    0.47
     Australia
    0.47
    ਾ
    0.47
     graders
    0.46
    POSITIVE LOGITS
     constable
    0.54
    ../
    0.50
     saka
    0.49
     дані
    0.48
     president
    0.47
     compelled
    0.47
     kupu
    0.47
     materiali
    0.46
     fæ
    0.46
     critic
    0.46
    Activations Density 0.000%

    No Known Activations