© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 90272
    Prev
    Next
    INDEX
    Explanations

    electronics

    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
    at
    0.68
    ס
    0.61
    λ
    0.52
     )
    0.50
    ৃ
    0.49
     </
    0.48
    ดูก
    0.48
     pien
    0.47
    תן
    0.46
    ย
    0.46
    POSITIVE LOGITS
    শিকান্ত
    0.59
    ಕ್ಕಾಗಿ
    0.54
    Пере
    0.54
    8
    0.53
    scoring
    0.52
     ఉన్నాయి
    0.52
    म्मी
    0.52
    Мо
    0.52
     Mạnh
    0.52
    highscore
    0.51
    Activations Density 0.000%

    No Known Activations