© 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. 107314
    Prev
    Next
    INDEX
    Explanations

    political parties and affiliations

    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
     possibility
    -1.05
     —
    -1.00
    сов
    -0.91
     возможно
    -0.90
    or
    -0.90
     וא
    -0.87
     grumpy
    -0.85
    ても
    -0.84
     praticamente
    -0.82
    toCharArray
    -0.80
    POSITIVE LOGITS
    goers
    1.73
     affiliation
    1.21
     hereto
    1.14
     organizador
    1.12
    affiliation
    1.09
    yyyyy
    1.08
    ilerin
    1.07
    yyy
    1.06
    鈇
    1.05
     parseFrom
    1.05
    Activations Density 0.016%

    No Known Activations