© 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. 54047
    Prev
    Next
    INDEX
    Explanations

    togetherness or partnership

    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
     }^{*
    -1.01
     one
    -0.99
     *}$
    -0.94
    licopter
    -0.94
     …
    -0.93
    欖
    -0.93
    mación
    -0.93
     mieć
    -0.92
    onsumsi
    -0.92
    joit
    -0.91
    POSITIVE LOGITS
     Together
    1.95
     together
    1.66
    Together
    1.59
     keduanya
    1.36
    together
    1.35
     latter
    1.20
     both
    1.20
    tiéndose
    1.20
     Their
    1.19
     insieme
    1.19
    Activations Density 0.086%

    No Known Activations