© 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. 118031
    Prev
    Next
    INDEX
    Explanations

    programming syntax or code elements

    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
    itamente
    -1.02
     eksklu
    -0.94
     årets
    -0.93
    ÁN
    -0.91
     января
    -0.90
     fjor
    -0.88
     開封
    -0.85
    っき
    -0.84
    гант
    -0.84
    istungs
    -0.83
    POSITIVE LOGITS
     would
    1.15
    }
    1.03
    ();}
    0.96
    }
    0.95
    endif
    0.93
     Jahrhunderts
    0.84
    *}
    0.83
    哺
    0.82
     />
    0.82
     and
    0.82
    Activations Density 0.010%

    No Known Activations