© 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. 31-GEMMASCOPE-2-RES-16K
    7. 5084
    Prev
    Next
    INDEX
    Explanations

    recovery, rem, Detective

    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
    ؛
    0.38
    ،
    0.38
    ፣
    0.37
    性格
    0.36
    .+
    0.36
    стере
    0.35
     ؛
    0.35
    করণ
    0.34
     многое
    0.34
    Extras
    0.34
    POSITIVE LOGITS
     通过
    0.38
     그
    0.37
     没有
    0.37
     特に
    0.35
    因為
    0.34
    没有
    0.33
    应该
    0.33
    খ
    0.33
    伙
    0.33
     are
    0.32
    Activations Density 0.317%

    No Known Activations