© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99973
    Prev
    Next
    INDEX
    Explanations

    recommendation and related words

    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_34/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
     {
    -1.37
    ]
    -1.28
    小花
    -1.20
    }
    -1.15
     distintas
    -1.15
    後記
    -1.11
    革
    -1.10
    抉
    -1.07
     estén
    -1.05
    ⻓
    -1.04
    POSITIVE LOGITS
     recommend
    1.81
    Recommended
    1.80
    recommended
    1.80
     Recommend
    1.73
     Recommendation
    1.65
     Recommendations
    1.61
     Recommended
    1.57
     RECOMMENDED
    1.53
     Recom
    1.53
    recommend
    1.52
    Activations Density 0.016%

    No Known Activations