© 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. 98071
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun or quantifier plus options

    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
    Lmfao
    -0.96
    🏷
    -0.91
    subseteq
    -0.86
    ensatz
    -0.84
    ————————
    -0.82
    嗗
    -0.82
    Fuckin
    -0.82
    landais
    -0.81
    Rgds
    -0.81
    okość
    -0.81
    POSITIVE LOGITS
     options
    8.38
     option
    7.03
    options
    6.03
     Options
    5.63
    Options
    5.38
    option
    5.16
     opciones
    4.94
    Option
    4.84
     Option
    4.75
     OPTIONS
    4.63
    Activations Density 0.171%

    No Known Activations