© 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. 4696
    Prev
    Next
    INDEX
    Explanations

    helpful and harmless

    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
     тощо
    0.38
    '.
    0.35
    ᱾
    0.35
    ؟
    0.34
     verder
    0.34
    Autres
    0.34
     інших
    0.33
    ។
    0.33
    ".
    0.33
     الأخرى
    0.33
    POSITIVE LOGITS
     имеет
    0.45
     has
    0.41
     έχει
    0.41
     tiene
    0.40
     असून
    0.39
     있으며
    0.37
     a
    0.37
    していますが
    0.36
     we
    0.35
     имеют
    0.35
    Activations Density 0.269%

    No Known Activations