© 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. 34-GEMMASCOPE-RES-131K
    7. 103897
    Prev
    Next
    INDEX
    Explanations

    ranked, ranking, rankings

    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
    Vapour
    -0.87
    Esti
    -0.85
    WEBP
    -0.83
    koord
    -0.79
    ]+=
    -0.79
    itakan
    -0.79
    žová
    -0.79
    醣
    -0.79
    效益
    -0.78
    ேன்
    -0.78
    POSITIVE LOGITS
     Wallet
    1.34
    Wallet
    1.24
     ranked
    1.16
     ranking
    1.14
     rankings
    1.11
     Ranking
    1.08
     liv
    1.05
    Ranking
    1.05
    RANK
    1.04
    ranked
    1.02
    Activations Density 0.040%

    No Known Activations