© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8280
    Prev
    Next
    INDEX
    Explanations

    multiple choice questions

    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_31_width_16k_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
    音
    0.42
    Pass
    0.40
    <sup>
    0.37
     rencontrer
    0.37
    ître
    0.37
    Justin
    0.37
    水
    0.37
     audio
    0.36
    XP
    0.36
    ```
    0.36
    POSITIVE LOGITS
     Sars
    0.42
     Commod
    0.41
     Surname
    0.41
     Σ
    0.39
     نفسه
    0.38
     Η
    0.38
     frown
    0.38
    هُ
    0.38
     месе
    0.38
     Martyrs
    0.38
    Activations Density 0.024%

    No Known Activations