© 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. 11052
    Prev
    Next
    INDEX
    Explanations

    laying the groundwork

    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
    rfloor
    -2.28
    }
    -2.13
    ቍ
    -2.11
    )$,
    -1.97
    msgTypes
    -1.94
    itemBuilder
    -1.93
    ();
    -1.91
    蕷
    -1.91
    |}{\
    -1.91
    ാന
    -1.91
    POSITIVE LOGITS
    </strong>
    1.94
    、“
    1.93
    resposta
    1.89
     considerada
    1.89
     ardından
    1.88
    ーめん
    1.82
     intriguing
    1.80
    -
    1.80
     
    1.75
    carrinho
    1.73
    Activations Density 0.005%

    No Known Activations