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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 6368
    Prev
    Next
    INDEX
    Explanations

    relationships, work, or tasks

    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_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
    ៕
    0.44
    }}
    0.41
    </h2>
    0.39
    ֖
    0.39
    ].
    0.37
    ”。
    0.37
    ".
    0.37
    .}
    0.37
     appunto
    0.37
     very
    0.37
    POSITIVE LOGITS
     কিংবা
    0.68
     mesela
    0.65
    、
    0.64
    したり
    0.64
    ၊
    0.62
     ebenso
    0.55
     、
    0.55
    はもちろん
    0.55
    ,
    0.55
    ፣
    0.55
    Activations Density 0.339%

    No Known Activations