© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 70196
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by nouns

    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
    齊
    -0.93
    Dí
    -0.89
    թ
    -0.85
     şə
    -0.84
    machung
    -0.83
    ॠ
    -0.81
    сиона
    -0.81
    齐
    -0.81
    ķ
    -0.81
     Intervention
    -0.80
    POSITIVE LOGITS
     chances
    1.62
     cues
    1.56
     cue
    1.51
     rightful
    1.23
     chance
    1.19
    cue
    1.14
     frustrations
    1.07
     measurements
    1.05
     lumps
    1.05
     leave
    1.04
    Activations Density 0.004%

    No Known Activations