© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 105961
    Prev
    Next
    INDEX
    Explanations

    recv, recieved, delivered, Greatest, mvp

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    -2.58
    jenigen
    -2.53
    </b>
    -2.45
    </u>
    -2.39
    …”
    -2.38
    -2.38
    褔
    -2.38
     ähnlichen
    -2.33
    喑
    -2.31
    </strong>
    -2.30
    POSITIVE LOGITS
    鬭
    3.70
    𞤤
    3.39
    𓇼
    2.97
    栳
    2.86
    甞
    2.66
    𞤪
    2.64
    簠
    2.64
    穽
    2.58
    嗵
    2.58
    𞤮
    2.52
    Activations Density 0.001%
    No Known Activations