© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 15384
    Prev
    Next
    INDEX
    Explanations

    instructions given to models

    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
    ת
    0.41
     Determine
    0.39
    ಗಳನ್ನು
    0.36
     ఉపయోగ
    0.35
     Minimize
    0.34
     వాటి
    0.33
     minimize
    0.33
     Customize
    0.33
     Unauthorized
    0.33
    సరం
    0.33
    POSITIVE LOGITS
    ě
    0.40
    ār
    0.39
    AN
    0.38
     choroby
    0.38
     mě
    0.37
     čo
    0.37
    I
    0.37
     není
    0.37
     saben
    0.36
     veľmi
    0.36
    Activations Density 0.013%

    No Known Activations